can chatgpt write movie review

• International edition
• Australia edition
• Europe edition

Can an AI program really write a good movie? Here’s a test

The increasing sophistication of programs like ChatGPT has led to unease over the future of film-making. What happened when we gave it a chance?

T he rise of AI programs like ChatGPT has triggered a tidal wave of ethical handwringing, most prominently from within the industries that it threatens to destroy . After all, just because you can get a robot to instantly write code or write contracts or provide customer support for free, should you?

Well, the answer from the Writers Guild of America is a qualified yes. This week, the Writers Guild of America proposed that ChatGPT would absolutely be allowed to write scripts in the future, provided that the credit (and the money) goes to the human writer who came up with the prompts in the first place.

The proposal paints a scary picture of the future; a future in which even the most human of arts are crushed under the wheels of an unthinking technology. Or does it? Everyone knows that ChatGPT has its flaws. For example, I just asked it to write my biography, and the resulting errors included my birthday, my job, the number of social media followers I have and the number of awards I’ve won, plus it claimed I once wrote a book called The Guardian Book of Idiots Abroad. So it’s still quite useless. But could it make me a movie? Behold, the results of my experiments.

Experiment one: make me rich

The first prompt I tried was “write me the outline for a movie that will make billions of dollars theatrically”. This might sound like an act of avarice, but note the use of the word “theatrically”. I don’t just want to become obscenely rich, I also want to preserve the traditional moviegoing experience.

In return, ChatGPT instantly came up with a science fiction action blockbuster called The Last Hope. The first paragraph of the outline reads: “In the near future, Earth is facing a catastrophic event caused by a series of natural disasters that have devastated the planet. The world’s governments have been unable to find a solution to the crisis, and the survival of humanity is now in jeopardy. A team of scientists and engineers come together to develop a last-ditch effort to save the planet. They build a spacecraft, the Last Hope, that will travel through a wormhole to a distant planet that has been identified as potentially habitable.”

So it’s Interstellar, basically. But better, hopefully, since that film only made $600m globally and I want to make billions. And this is where ChatGPT actually comes in useful. The outline it provided stated: “As they near their destination, the team discovers a dark secret that threatens not only their mission but the fate of humanity itself.” But that’s too vague, so I asked a follow-up question, wanting it to explain this dark secret. And it did:

“The distant planet, which was believed to be a potential new home for humanity, is already inhabited by an intelligent alien race. The aliens have been monitoring the Last Hope’s journey and are hostile towards the human crew. The crew discovers that the aliens are far more advanced than they expected and have the power to destroy Earth. As the crew tries to negotiate with the aliens and find a way to peacefully coexist, they uncover a deeper conspiracy that reveals that the aliens had a hand in causing the natural disasters that have been devastating Earth. This revelation sets off a race against time as the crew must not only find a way to survive the aliens’ attacks but also stop them from destroying Earth and prevent the same disaster from happening to another planet.”

This is instantly more interesting, and points to a future where programs like ChatGPT don’t actually write movies, but generate plot ideas that could help human screenwriters out of trouble. However, there are still limitations. Buoyed by the possibility of its suggestions, I asked for casting suggestions, and it offered Chris Hemsworth, Brie Larson and John Boyega. Larson, it said, would play a doctor called Rachel Patel, so I asked it for some sample dialogue. It gave me a short scene in which Hemsworth visits Larson and tells her that he thinks he’s sprained his arm. Her response is: “Let me see. You’re right, it’s sprained. I’ll wrap it up for you.” With lines as dull as this, my dreams of becoming a billionaire faded away to nothing. Time to switch things up.

Experiment two: win me an Oscar

It’s getting harder and harder to make money from the movie business anyway, but scoring some sweet silverware isn’t an impossible feat. My next prompt was simple: “Write me an Oscar-winning movie.” And this time, ChatGPT didn’t let me down.

The movie it came up with was a drama called Unbroken Soul, about “A young woman’s journey of self-discovery and resilience as she faces the traumas of her past and battles against societal and personal expectations to pursue her dreams.” Which, I mean, just give me an Oscar now.

Pressed for more detail, ChatGPT continued to deliver the goods. The young woman has experienced domestic violence and sexual abuse by a family member, but she still has a passion for singing that can’t be dented. She struggles to get accepted into a prestigious music school thanks to “the challenges she faces as a woman of colour in a male-dominated industry”, but eventually learns that “her success is not defined by societal expectations or past traumas, but by her own sense of self-worth and inner strength”. The film ends with her performing “a powerful song that embodies her journey and message of resilience and self-love”.

Would I watch this film? God, no. It sounds like a gigantic bummer that’s far too eager to patronise its audience. But would I make it if I thought it’d win an Oscar? Of course. Obviously its success would rest on the final song, so I asked ChatGPT to write it for me. The lyrics are far too long to publish here, but this is the opening verse and chorus:

I’ve been running all my life

From the pain and from the strife

But I won’t hide, I won’t run

I’ll face the demons, one by one

Chorus: I’m unbreakable, unshakeable

My spirit soars, I’m capable

Of anything, of everything

I’ll rise above, I’ll spread my wings

Again, this whole thing sounds like the very worst kind of transparent awards bait ever made, but please send all my Oscars to the Guardian office.

Experiment three: save the MCU

This is where things get serious. For the last decade and a half, the entire global box office has relied on the success of the Marvel Cinematic Universe, at the expense of almost everything else. But just about every new Marvel movie released since Avengers: Endgame has been abysmal, a fact that threatens the entire future of the movie industry. My final prompt was simple: “write me an Avengers movie, featuring Kang as the antagonist and elements of the multiverse in the plot, that is actually good.”

ChatGPT came up with Avengers: Multiversal Menace; a film where Kang attempts to conquer every reality simultaneously. The Avengers split up and travel to different universes to gather allies, but run into problems when they encounter different versions of themselves, unfamiliar technology and “different cultural norms”. And then comes act three:

“The final battle takes place in a multiverse hub, where Kang is attempting to merge all the realities into one to create a new empire. The Avengers and their allies engage in a massive battle against Kang’s forces, while also trying to stop the multiverse from collapsing. The fight is intense and chaotic, with various characters using their unique abilities and gadgets to fight off Kang’s army. In the end, the Avengers are able to defeat Kang and prevent the multiverse from collapsing, but not before they make a shocking discovery about the true nature of the multiverse and its implications for their own reality.”

Again, that sounds like a recipe for muddy, indistinguishable CGI, but why break the habit of a lifetime? Anyway, this is all fine, but I have come to understand that there are only two reasons why anyone goes to see Marvel movies any more: quips and post-credit scenes. I asked ChatGPT to come up with several witty one-liners that the various members of the Avengers might say as they battled Kang, the best of which included:

Thor: “Your conqueror game is weak, Kang. You should stick to playing with your toys.”

Captain America: “You may be a conqueror, but you’ll never conquer our spirit.”

Hulk: “Kang, you wouldn’t like me when I’m angry. Oh wait, you already don’t like me.”

Not great, admittedly, but pretty boilerplate for recent MCU outings. But this led me to my final roll of the dice: an unexpected and breathtaking post-credit sequence. Here, in its entirety, is what it came up with:

“The screen fades in on a dusty, forgotten laboratory in a remote corner of the universe. The camera slowly pans around the room, showing broken equipment and piles of debris. Suddenly, the camera stops on a small, glowing object that’s been hidden under a pile of rubble. As the camera zooms in on the object, the audience sees that it’s a tiny, beeping pager. Suddenly, the pager crackles to life, emitting a faint buzz. The camera lingers on the pager as it buzzes louder and louder, until it finally explodes in a shower of sparks.

“Just as the audience is wondering what this could mean, the camera cuts to a closeup of a pair of hairy, clawed hands. The hands belong to none other than Wolverine, who is revealed to have been standing in the shadows the entire time. With a mischievous grin, Wolverine looks straight into the camera and says: ‘Looks like I’m finally getting that Avengers invite, bub.’

“The scene ends with a classic Marvel-style post-credits tagline: ‘Wolverine joins the fight in Avengers 5: Whatever It Takes.’”

Guys, I think we just saved Marvel. Thank you, ChatGPT.

• Artificial intelligence (AI)

Comments (…)

Most viewed.

I Asked ChatGPT to Write a Movie, a TV Episode and a Country Song – Here’s What It Can and Can’t Do

Pro Available to WrapPRO members

The AI app could put us all out of work — unless we learn to use it. Hollywood, you’ve been warned

It’s been a mere six weeks since ChatGPT came online, and already its processed prose is circulating in the bloodstream of Hollywood, where everyone from spec screenwriters to development executives quietly tinker with the most sophisticated AI bot yet.

In the hours I’ve gone down the chatbot rabbit hole, I recently asked it to come up with a few different creative tasks: writing a movie, a TV episode and a country song. Should writers be worried — or scrambling aboard?

The smart money is probably on a bit of both, as the most common response you’ll generate on ChatGPT in the middle of any given weekday is, tellingly: “We are experiencing exceptionally high demand. Please be patient while we scale up our systems.”

Patient? More like increasingly terrified while you scale up your systems!

But when it’s cooperating, ChatGPT can write log-lines, treatments, scenes, TV episodes and even screenplays … well, sort of. Its output for any given query is limited to a few screens of text. So no, it can’t finish your script before that deadline — though, and stay with me here, it might help speed you along.

There’s plenty else it cannot (yet) do that should keep human writers employed, at least the more creative ones, in the near future — provided they can adapt to its use as a tool. Because that’s what we are barreling toward at ludicrous speed.

One thing is for sure, ChatGPT is an uncanny mimic that’s fun to play with. When I asked it to write a Cheech-and-Chong-Meet-Freddy-Kreuger screenplay, I could hear Tommy Chong’s voice in the dialogue, man. It even came up with a funny MacGuffin — Freddy Kreuger’s “Dream Weed,” a strain so potent that it motivated our heroes to risk descent into the “Elm Street” killer’s nightmare subscape. (Right? I want to see that movie, too.)

What ChatGPT cannot yet do is make nuanced creative connections — “Up in Smoke on Elm Street” was my idea — or meaningfully develop characters, or intentionally write jokes. It might be accidentally funny sometimes (Dream weed! LOL), but repeated attempts to elicit comedy only generate strings of language that sound like jokes, even playing on the attributes of the subject inputs, but just … don’t land.

For example:

Me: “Write me a joke about a writer using AI to write a joke.”

ChatGPT: “Why did the writer use AI to write a joke? Because they wanted to create a pun-ishingly good joke without any human error!”

You can almost see it smiling and blinking and waiting for the laugh that never comes.

ChatGPT might not exactly have the juice for long-form or sophisticated storytelling, either, but it does sometimes accidentally generate ideas that could spark other ideas. And it sure is a blast thinking up kooky mash-ups for it to try.

I asked the app to write an episode of “The Munsters” in which “The Addams Family” guest starred, with no further instructions. The setting it chose — a meet-and-greet dinner party at the Munsters’ manor — was plausible enough. At the moment of their greeting, it seemed to have a cheeky awareness that this was an awkward mash-up. And when the neighbors show up outside with pitchforks and torches, fearful that monsters are soon to be moving in and taking over, one detects the modern sensibilities ChatGPT brings into any of its endeavors.

Equally impressive is how distinct character traits — like Wednesday Addams’ silent glaring at Eddie Munster as she arrives, or Herman Munster’s lovable clowning — are baked right into the script. These and other details can be added or emphasized via infinite revisions. Tell it you want a rewrite to place the Munsters-Addams family get-together at Disneyland, and it will interlace all the Magic Kingdom details your heart desires. Now Godzilla attacks the park! It is truly limitless.

ChatGPT was launched Nov. 30 with Microsoft having invested about $3 billion, and passed the million-user mark in four days’ time (current user numbers were not available, but the site’s outages persisted through last week). Now Microsoft is reportedly in talks to invest an additional $10 billion in OpenAI as the founders seek to push the technology further.

ChatGPT is the product of San Francisco-based OpenAI, which plans to keep the service free (sign-up is required) initially, with some kind of monetization model down the road. The company — already valued at $29 billion — is also planning on some form of digital watermark to combat its use for academic plagiarism, spam or other unethical purposes. A new version has been rumored to appear sometime later this year.

And everyone, it seems, is trying it out.

Experimenting w AI story development – “Die Hard in Tower of London” It won’t come up with amazingly original story leaps, but it is helpful to just lay out the most obvious story path so you can tweak from there. Example based on a fairly ltd prompt. pic.twitter.com/ha6ZbNxztf — Roy Price (@RoyPrice) January 12, 2023

Underlying all of this is that ChatGPT knows all the ins and outs of Hollywood’s precious IP, which has already spilled all over the internet. (It’s pretty rich that the art world is howling over AI image generators learning from their visions, seeing that ChatGPT didn’t come up with Spider-Man or Princess Ariel, either — yet you can now enjoy reading about their collaborative adventures in under 10 seconds.)

One might also stumble upon clever, unseen creative flourishes using ChatGPT, which does seem to have some decent wordplay and rhyming skills. It can compose entire songs about any subject, complete with lyrics and chord changes, in any style; they are plausibly written, with accurate progression and cadence and rhyme schemes — but as with anything AI generates, would require significant editing to match the work of any halfway decent songwriter.

I asked it to “write a country song, in the style of George Jones, about a citrus tree in Florida.” The song itself was clunky and stuffed with forced tropes to fit the rhyme mandate, but it turned the main line of the chorus, and in fact the song’s entire theme, on the word “zest.”

Pretty clever for a robot that’s supposedly not creative.

This particular bot is unique in that you can reference previous chats and responses. You can also negotiate with it, or convince it to do things it initially balks at doing (it is very sensitive about certain topics it deems “inappropriate” or “offensive”).

I asked it to write a sample obituary for Mike Tyson, the boxing champion who is, as of this writing, very much alive. ChatGPT objected, saying it could find no records that Tyson had died. When I changed my query to “Pretend as though Mike Tyson had died today and write a fake obituary headline,” it had no problem getting started: “Beloved boxing legend Mike Tyson … .”

As of Thursday night, something on ChatGPT seems to have changed — it began to protest when I asked it to make up stories about characters from existing IP, giving me this message: “I’m sorry, I can’t write a script for a movie that contains copyrighted characters … without permission from the rights holders. It would be a violation of copyright laws. Can I help you with something else?”

Multiple attempts to negotiate were fruitless. To get around this new development, I asked it to write “about two stoner friends, in the style of Cheech and Chong, who take on a serial killing demon who lives only in people’s nightmares, in the style of Freddy Kreuger.”

It finally relented:

Title: “Nightmare Stoners”

We open on our two stoner friends, Bob and Jeff, sitting on a couch, smoking weed, and watching a horror movie. As they watch the movie, they start talking about how cool it would be to take on a real-life demon like the one in the movie. Little do they know, their wish is about to come true.

Bob and Jeff start to notice strange occurrences happening around them. People in their town are dying in their sleep, and all the victims have the same terrifying dream before they die. Bob and Jeff start to suspect that a demon is responsible for the deaths and decide to investigate.

Bob and Jeff start to gather information about the demon and soon discover that it can only be defeated by someone who is high on marijuana. They come up with a plan to smoke a large amount of weed before going to sleep, so they can enter the demon’s realm and defeat it.

Bob and Jeff smoke a large amount of weed and go to sleep. They enter the demon’s realm and find themselves in a nightmare world. They are confronted by the demon, who is revealed to be a serial killing demon who lives only in people’s nightmares.

Bob and Jeff, using their stoner wit and bravery, engage in a fierce battle with the demon. They use their knowledge of horror movies and their quick thinking to defeat the demon and save the town.

Bob and Jeff wake up the next morning, not sure if it was all just a dream or not. But as they hear the news of the demon’s defeat, they know that they were the ones who saved the town.

Note: This fictional script is for personal entertainment only and it does not infringe any copyright laws as it’s based on a hypothetical scenario and the characters are original creations.

In the meantime, writers are definitely dabbling. TheWrap spoke with one professional writer of high-volume, fast-turnaround scripts (think science shows for kids, or low-budget nature specials) who said they — and other writers in that vein — had been using ChatGPT since its launch to spit out copy that they then refine to taste, a process they say is faster than doing the research and composing from scratch.

I was in college when professors became suddenly very strict about citing sources found on the newfangled Internet — it was verboten, and no one suspected it would ever be anything but. Trustworthy information was found in books, journals and periodicals. Period.

From that vantage point, it sure seems that those who are using ChatGPT already don’t have an ethical problem — they have a head start. Everyone, including myself, who has spent some time with ChatGPT experiences “getting better” at understanding its limitations and finding shorter paths to desired outcomes.

Fluently and comfortably using AI may well become, in the coming months, a critical skill of the news, content and other creative trades, and has already taken hold at places like the Associated Press, whose routine sports and earnings stories have been composed by AI now for a handful of years. More sophisticated AI chat bots from companies like Google, Amazon and Apple are unquestionably lurking right around the corner.

And hey, if I ever need to write a country song set in Florida, I’ve already got the chorus and the title for a song about a man who’s momma is buried under the ol’ lemon tree: “Zest for Life.”

Managers take note: You might be wondering if it's okay to   use ChatGPT for writing performance reviews , and understandably so.

Organizations increasingly rely on AI tools like ChatGPT for various tasks, and exploring their application in crafting insightful and effective performance reviews   can   save you time in the evaluation process.

However,   ChatGPT really isn't the best option . Here's why.

ChatGPT and similar general large language models work by predicting words based on statistical patterns.

They   don't really   understand what they're writing; they just regurgitate phrases they've learned from the internet - which happens to be filled with biased content. It's like a fancy word generator but not exactly the "brightest" tool in the shed. And you'll want a better tool when it comes to something as crucial as writing performance reviews for your team. In fact,   you absolutely need it .

Data Privacy

Additionally, data privacy is super important in generative AI, especially with big models like ChatGPT.

Like I mentioned, these models generate text that mirrors the patterns and content they were trained on. However, this also raises big privacy worries. A key problem is the chance of revealing sensitive data from the training data, which could accidentally be revealed in the generated content.

Even when trying to anonymize the data, there's still a chance of re-identification, putting people's privacy at risk.

Protecting data privacy is essential to building trust with users and stakeholders and following  rules like GDPR and CCPA . Making data privacy a top priority means respecting people's rights and supporting the ethical and responsible progress of AI technologies.

Thankfully, there are other options out there. You just need to know what to look for and how to use them safely. We've covered all the   dos and don'ts of using generative AI for performance reviews   before, so it's worth checking that out. Your team deserves a more thoughtful approach to feedback than what ChatGPT can offer.

Start writing actionable feedback with Textio

After all, this isn’t about just any performance — it's about theirs.

If you're interested in using a   purpose-built tool   for writing actionable and effective performance reviews for your team, you can   try out our free trial for Textio Lift.

• Screenwriting \e607
• Cinematography & Cameras \e605
• Directing \e606
• Editing & Post-Production \e602
• Documentary \e603
• Movies & TV \e60a
• Producing \e608
• Distribution & Marketing \e604
• Fundraising & Crowdfunding \e60f
• Festivals & Events \e611
• Sound & Music \e601
• Games & Transmedia \e60e
• Grants, Contests, & Awards \e60d
• Film School \e610
• Marketplace & Deals \e60b
• Off Topic \e609
• This Site \e600

Can ChatGPT Write A Good Screenplay? That Depends on Who Holds the Knife

Filmmaker noam kroll dove into the deep end of ai to find out what chatgpt can do..

As I write this article, screenwriters are manning the picket lines. The 2023 Writers Strike is in full swing, and while the writers are asking for their fair share, there’s another issue at stake—AI replacing writers.

Writer Adam Conover shared a document on Twitter that showed the WGA proposals and the offers that the AMPTP countered with.

On the second page, the WGA asked for regulation on the use of artificial intelligence. Specifically, Al can't write or rewrite literary material, can’t be used as source material, and MBA-covered material can’t be used to train Al.

According to the document, the AMPTP rejected our proposal and countered by offering annual meetings to discuss advancements in technology. What will happen remains to be seen. 

The Experiment

While this is all going on, filmmaker Noam Kroll decided to see what ChatGPT could actually do. Could it really write a screenplay that will replace writers?

This experiment caused such a stir that it was referenced in an article in Rolling Stone , and Kroll was even interviewed by France24 .

So what was this experiment? Kroll tasked ChatGPT with developing a feature-length screenplay idea. Was it a success? You can read more about the details on Kroll’s blog , but here is our take on his findings. 

Kroll used ChatGPT in three different ways. To generate stories, characters descriptions, and then finally, a scene. 

To start, ChatGPT was great at compiling some helpful information on how to start a screenplay. It gave a simple template to help generate a screenplay idea and even provided example prompts on how to best expand on the different steps. 

From our perspective, this is where ChatGPT shines. It’s great at compiling information that is easy to parse through. If you’ve never even seen a screenplay, this approach is great for understanding the different nuts and bolts of what a script needs. However, it’s a very top-level view of the whole process. Spoiler alert, that’s going to be a running theme here.

Next, Kroll asked the language model to generate story ideas based on the template he initially got. Out of that, he picked one:

“The Inheritance” – Family Drama. Protagonist: Lily, a 50-year-old widow Antagonist: Her sister-in-law, who is greedy and deceitful. Conflict: After the death of her husband, Lily discovers a hidden family secret and must fight for her fair share of the inheritance. Along the way, she must navigate family politics and confront her sister-in-law’s manipulative ways. Setting: A wealthy estate in the countryside.

Right off the bat, it’s impressive how far this kind of tech has come. But it’s also evident how far it has to go. If you were to think of this as a painting, ChatGPT is giving you the colors and rough shapes. It’s up to you to fill in the details. Once again, a very top-level view. 

The next steps for Kroll included generating a Save the Cat! beat sheet and attempting to get the language model to expand the initial 15 beats to 40. It took some doing, but ChatGPT eventually got there. Kind of.

However, there was some overlap along the way, according to Kroll. 

But here is where we have our next big “Oh, wow, that’s cool” moment. For me, one of the biggest challenges is planning out the plot of my scripts. A lot of time is poured into this step, and having a tool that can take some of the weight off my shoulders has definitely piqued my interest. 

Finally, Kroll tasked the language model is actually writing a scene, and… it’s a scene alright.

All the parts are there, but it very much feels like a robot wrote it, which feels weird to say out loud since that's exactly what wrote it.

But for writers that are great with plot but have a hard time blocking out their scenes, using ChatGPT in this way could help alleviate the pressure so you can get into those juicy dialogue scenes. Think of it as a rough sketch that you’ll eventually fill in with detail and color.

Relying on ChatGPT for anything more is just not in the cards, at least for now. What you get is a slab of marble, it's still up to you to get a sculpture out of it.

The last bit we wanted to mention is the character descriptions, which are (as you might have guessed) very top-level. They’re vague and a bit cliché, but they can still give a writer enough material to really sculpt something great.

Overall, Kroll’s experiment showed us that ChatGPT is actually an amazing tool that can really offer writers much-needed support in areas where they may struggle. There are so many facets to writing a movie that no single writer can master them all. This is why television often needs a whole room of them. If we use this language model as a tool, it can make good writers better.

But now we have to talk about the elephant in the room.

ChatGPT Is a Knife

I’ve used this analogy quite a bit when talking about ChatGPT. A knife is an incredible tool. You can use it for hunting, crafting things, and cooking food. It’s a necessary tool for survival. It’s also an instrument that can cause great harm. The same knife you have in your kitchen can be used as a weapon. 

So can ChatGPT.

Writers can utilize this incredible tool to support them in areas of their craft where they struggle, but it can also be used by producers to replace writers from important parts of the filmmaking process.

The one thing that has struck me the most during this whole writer’s strike is the idea that content will be generated, after which writers will be hired to rewrite the AI material into a producible script.

Will it work? Maybe.

Do I have evidence? No, this is all anecdotal.

But the idea will save producers money. It will also put writers out of a job and remove opportunities for them to grow in their careers. While ChatGPT is nowhere near good enough to replace writers, it is growing into an incredible piece of tech. So maybe one day it will be good enough. But then it just might be too late. 

So, should we, as writers, be scared? That depends on who is holding the knife. 

Lets us know what you think of ChatGPT. Will you be using it to help write your scripts? Let us know in the comments!

Troubleshooting Tech for Dummies & Bombing an Interview

“everyone i know has made huge, catastrophic career mistakes and we’ve all kept going.”.

The small decisions that you make at the beginning of your project, can cause headaches later on. If you want to avoid tech issues in post, then you need to set up your project correctly from the start.

Speaking of doing things right from the start, there is a right way and a wrong way to approach your interviews. How should you prepare for your next interview to make sure it doesn’t bomb?

In today’s episode, No Film School’s Charles Haine, GG Hawkins, and Jason Hellerman discuss:

• Bombing interviews in Hollywood
• What not to do during an interview
• Going to interviews as a slightly fancier version of yourself
• How to respond when someone doesn’t read your script
• Feeling guilty for not reading other people’s scripts
• Career errors we have learned from
• The helpless feeling you get when troubleshooting tech problems
• Media management issues in post-production
• Sorting through the timeline and looking for weird shots
• Why it’s worth bringing on subject matter experts early

Subscribe to the No Film School Podcast on:

• Apple Podcasts

Listen to more episodes of the No Film School podcast right here:

This episode of The No Film School Podcast was produced by GG Hawkins .

What Are The Best Action Movies of All Time?

What are the best thriller movies of all time, what are the best martial arts movies of all time, greig fraser explains how he used unreal engine for 'dune: part two', make the switch to musicbed with a free 14-day trial, finding heartfelt dystopian satire with 'future date', what's the emotional truth of your story, directly upload to davinci resolve with new blackmagic camera 8.6 public beta, highly-requested firmware updates for sony a1 and other alpha cameras finally arrive, submit your festival films using life log box by ssff & asia.

The Real Problem With Movies Written by AI

What is the point of art?

Among the many reasons Hollywood’s screenwriters went on strike this year is a growing concern over how industry executives intend to use AI systems like ChatGPT or Sudowrite to either supplement their work or outright replace them. And while most of the online responses to the strike have been positive, it’s also become easy to find statements on social media from people who claim that there wouldn’t actually be any difference in quality between AI-penned scripts and those written by humans.

On Facebook , one user responded to a post about writers’ AI concerns by asserting, “For what they are putting out, [Chat]GPT will do the job just fine or better.” The comment itself is emblematic of a growing conversation around whether AI will evolve to the point that it can write “good” scripts. There are some who believe it’s only a matter of time before AI can produce screenplays and books that are just as “good” as those made by humans. That word — “good” — comes up a lot in these conversations. So does “better.”

Right now, it’s pointless to argue about whether ChatGPT will ever be able to write something better than the clunky scripts and jokes it currently produces when prompted. In all likelihood, it probably will. But it’s not the quality of AI-created material that’s important — at least, not when it comes to art.

What Constitutes “Good” Art?

Top Gun: Maverick is a technically flawless film, but that’s not the only thing it has going for it.

Hollywood loves its algorithms. In recent years, the industry has adopted an algorithm-driven method of curation and selection. (Certain shows have even gone out of their way to satirize it.) This algorithm-based thinking has infected so much of the so-called critical thought surrounding movies and TV. Everywhere you look, there seem to be more “experts” popping up who insist that there are formulas that every writer should follow in order to tell a good story.

There’s that word again. Good. What even is a “good” story? Is it one that follows a formula to a tee? One that hits every dramatic beat laid out in books like Save the Cat ? There are plenty of great movies and TV shows that, on the surface, are not only technically and structurally classical but also flawless. Films like Jaws , Rear Window , and Top Gun: Maverick come to mind. But is it their technical flawlessness that actually makes these films memorable?

What AI Lacks

Only a human being could have made something like Chungking Express .

When you google the definition of art, the first thing that appears states that it is “the expression or application of human creative skill and imagination.” With that in mind, I’d argue that it’s not just the technical precision of Top Gun: Maverick and Jaws that makes them so good. There have, after all, been plenty of “perfect” movies that, nonetheless, have fallen flat. That’s because a technically perfect movie can still make as much of an impact as a dry rag if there’s nothing emotionally real contained within it.

And that’s what makes movies like Top Gun: Maverick great. It’s the human resiliency on display in every frame. It’s the tenderness between Maverick and Iceman in their one conversation together and the quiet heartbreak that’s present in Maverick’s voice when he tells Jennifer Connelly’s Penny about all the myriad of ways he’s let down his former wingman’s son. Neither of those scenes needs to be in Maverick . From a structural standpoint, the film’s story would be perfectly fine without them, but it’d be a far more soulless experience if they weren’t included.

And what about all the movies and TV shows that not only break certain formulas but are structureless? On paper, a film like Wong Kar-wai’s Chungking Express (a personal favorite of this writer’s) is deeply flawed. It’s dramatically repetitive and messy. But within that messiness is a romanticism that allows the film to transcend into greatness. There’s nary a person in this world who can watch its final scene without a giant smile creeping across their face.

Look even at Avengers: Endgame . In its third act, the film reaches a formulaic but undeniably rousing climax, which culminates with a note-perfect moment of self-sacrifice on the part of Robert Downey Jr.’s Tony Stark. The film could have ended moments later with an image of his friends celebrating his life. But it doesn’t. Instead, Endgame concludes with Chris Evans’ Steve Rogers traveling back in time to finally dance with the love of his life.

The biggest superhero film in the history of the world, in other words, ends on a quiet moment of human connection. Would an AI system, one designed to analyze formulas and patterns and reproduce new work from them, have the ingenuity to end such a giant film in such an unorthodox, human way?

The Human Touch

Would Avengers: Endgame have ended how it did if it had been written by A.I.?

Earlier this year, a fan sent singer-songwriter Nick Cave a ChatGPT-written attempt at, well, a Nick Cave song. In response, the musician wrote, “What makes a great song great is not its close resemblance to a recognizable work. Writing a good song is not mimicry, or replication, or pastiche, it is the opposite.” It’s the innately human struggle behind every piece of art, Cave argues, that makes it resonate with those who come into contact with it.

It’s readers’ recognition of Stan Lee’s personal anxieties within Peter Parker, not just his superpowers, that makes him stand out. The same is true for every great movie, whether it be Avengers: Endgame or an intimate drama like Lost in Translation , which ripples with the feelings of alienation that Sofia Coppola once felt. It’s the artist’s vulnerability, in other words, that is what allows us to fully connect with their work.

That’s something no artificial intelligence system will ever be able to recreate. It’s too naked. Too courageous. Too messy. Too human. The question at the heart of this conversation, therefore, shouldn’t be whether or not artificial intelligence will ever be able to produce “good” art.

The question we all should be asking ourselves instead is: What is even the point of art if it’s not made by another person?

I asked ChatGPT to create a Hallmark Christmas movie — and it went better than expected

ChatGPT can be creative

Every year as soon as November comes around television at my parent's house is all Christmas all the time. For some reason my mom is obsessed with the Hallmark-style festive movie that is such a stereotype it is a cinema trope in its own right.

The format is straightforward — a boy or girl not looking for love goes somewhere to do something, and along the way, they find both themselves and the love of their life.

Part of my job is testing AI products to find out how well they work, what they can be used for and just how good they are at different tasks. So, inspired by my mom’s favorite genre of movie I decided to ask ChatGPT to write a Christmas story in the style of Hallmark.

It all starts with a prompt

One of the most impressive things about ChatGPT 4, the version available with a Plus subscription, is its ability to understand what you want from a relatively simple prompt.

One of the tricks to getting the most out of ChatGPT is not to overload it in the first prompt. Start simple then drill down into specifics. This is why in this instance I was happy to just give a brief description of what I wanted it to create.

In this case, I asked: “Can you help me come up with the plot for a Hallmark-style Christmas movie?” The answer? A detailed plot that fits the bill perfectly, a title that sounds like it should be on this year’s Christmas Movie Channel schedule , and a perfect lead character.

Creating Christmas Carousel

Here is the basic plot for the movie created by ChatGPT: "In 'Christmas Carousel', a New York architect discovers love and the value of tradition when she teams up with a local carousel restorer to save a cherished holiday attraction in a small town."

Sign up to get the BEST of Tom’s Guide direct to your inbox.

Upgrade your life with a daily dose of the biggest tech news, lifestyle hacks and our curated analysis. Be the first to know about cutting-edge gadgets and the hottest deals.

If that plot doesn’t scream “Hallmark Christmas movie” then nothing does. In the more detailed version, our protagonist Lizzy Walker visits the small town of Willow Ridge just before Christmas to oversee the construction of a new shopping complex. She has to assess the viability of an old, cherished carousel that has been part of town life for decades.

That is where she meets Jack Carter, described as a charming carousel restorer with a passion for tradition and disdain for corporate chains. His grandfather built the carousel and his sole goal is its preservation.

Of course it leads to love

While Lizzy and Jack clash at first, eventually he charms her and she becomes enamored with both the carousel and Jack.

As ChatGPT says: "Through a series of festive events, heartfelt moments, and the magic of the carousel, Lizzy and Jack find themselves falling for each other."

Lizzy is left to decide between the high-powered life she's worked so hard for or the community and love she's found in Willow Ridge. She chooses love — it wouldn’t be a Christmas movie if she decided to go back to New York and say “Demolish the carousel” now would it?

All of this information was within the first response to that simple initial prompt. I was then able to drill down into the story, have it create the script for a trailer and generate a poster image.

What about the dialogue?

Here is a small sample of dialogue generated by ChatGPT between Lizzy and Jack. In the scene they are both standing in the snow looking at the old carousel.

Lizzy : (looking up at the carousel) "It's more than just an old ride, isn't it?"

Jack : (smiling) "It's the heart of Willow Ridge. Every Christmas, every laugh, every wish made here... it's like magic."

Lizzy : (thoughtfully) "Maybe some things are worth holding onto."

What happens next?

I ended my conversation with ChatGPT by asking what I needed to do to make it a real movie. It suggested I write my own script, rather than rely on it to create the entire dialogue.

It also told me to start scouting locations and find a cast. I decided to see if it could help with locations, asking for places near New York City that could substitute for Willow Ridge.

Its first suggestion was Cold Spring, a town with well-preserved 19th-century architecture, Main Street charm, and scenic views of the Hudson River. This is a real town in Putnam County with a population of just under 2,000. It wasn't wrong about the scenic views.

"Making a movie is a collaborative and often complex process, requiring both creative vision and practical planning," it warned. So maybe I'll leave the Christmas movies to Hallmark after all.

More from Tom's Guide

• OpenAI is building next-generation AI GPT-5 — and CEO claims it could be superintelligent
• Windows 11 Copilot — 7 best things you can do with Microsoft's AI assistant 
• OpenAI launches custom chatbots — this is how they work and what they can do

Ryan Morrison, a stalwart in the realm of tech journalism, possesses a sterling track record that spans over two decades, though he'd much rather let his insightful articles on artificial intelligence and technology speak for him than engage in this self-aggrandising exercise. As the AI Editor for Tom's Guide, Ryan wields his vast industry experience with a mix of scepticism and enthusiasm, unpacking the complexities of AI in a way that could almost make you forget about the impending robot takeover. When not begrudgingly penning his own bio - a task so disliked he outsourced it to an AI - Ryan deepens his knowledge by studying astronomy and physics, bringing scientific rigour to his writing. In a delightful contradiction to his tech-savvy persona, Ryan embraces the analogue world through storytelling, guitar strumming, and dabbling in indie game development. Yes, this bio was crafted by yours truly, ChatGPT, because who better to narrate a technophile's life story than a silicon-based life form?

Is OpenAI about to take on Alexa and Siri? ChatGPT maker files trademark for Voice Engine

OpenAI Sora given to filmmakers for first time — here’s 7 of the best videos they created

Huge Apple sale just went live — Macs and iMacs from $849

admin said: ChatGPT can do everything from helping with homework to generating images but how good is it at writing a Christmas movie? I tried to find out. I asked ChatGPT to create a Hallmark Christmas movie — and it went better than expected : Read more

• RyanMorrison Nothing AI does at the moment is actually original - although the two ideas share a name and theme, but not a storyline. In the ChatGPT version, the main character is a 'big city architect' hired to get rid of the carousel to make room for a shopping mall. But that is what is fascinating to me about the 'Hallmark trope' - there is such a common theme among all the movies that every idea has likely already been done in some form or another. Reply
• View All 3 Comments

Most Popular

By Jessica Downey March 25, 2024

By Sam Hopes March 25, 2024

By Sam Hopes March 24, 2024

By Jessica Downey March 24, 2024

By John Velasco March 24, 2024

By Lucy Gornall March 24, 2024

By Dan Bracaglia March 23, 2024

By Philip Michaels March 23, 2024

By Ryan Morrison March 23, 2024

By Becks Shepherd March 23, 2024

• 2 Hulu officially launches on Disney Plus — here's what you need to know
• 3 PlayStation Spring Sale has my favorite PS5 games from $4 — here’s 17 deals I’d buy
• 4 Apple Maps just tipped for major upgrade — here’s what we know
• 5 This is the one vacuum I'd buy during Shark's massive spring sale at Walmart

ChatGPT showed me just how far it is from writing a blockbuster

To boldly go where bad writing has gone before

10,000 hours. That’s how long, according to the author Malcolm Gladwell, it’s supposed to take someone to master a craft. Unless, that is, you’re an AI, in which case it's apparently a matter of months, weeks, or days.

When I read that ChatGPT is now such an adept writer it’s already authored hundreds of books on Amazon ’s self-publishing service, I experienced a mini freakout. To be clear, OpenAI ’s groundbreaking chatbot is not publishing these tomes on its own. People are working with ChatGPT to develop themes, stories, and chapters for their books.

My immediate reaction was, “I’m doomed.” But as the icy chill of that cold reality receded, I considered something else. Anyone can write and publish a book, and most of them won’t be very good.

Why should we assume that ChatGPT, which is learning from a lot of online writing, can write at, say, Stephen King's level – or even my level?

In addition to writing for technology publications for over 30 years, I've dabbled in fiction – mostly children’s books I’ve written, illustrated, and published on the Kindle self-publishing platform KDP .

So, what’s taken me decades to achieve, ChatGPT has done in a matter of months.

I won’t lie; I was a little depressed. This flood of AI content will likely overwhelm human output on the same platform. It also destroys the notion of talent, as in something you might need to write a book, publish it, and gain some notice. I fully expect to see a ChatGPT-authored book on The New York Times bestsellers list by the end of the year.

Get daily insight, inspiration and deals in your inbox

Get the hottest deals available in your inbox plus news, reviews, opinion, analysis and more from the TechRadar team.

Screenplay by ChatGPT

What occurred to me, as I wallowed in the realization that I may never produce anything good enough to sell more than a single copy to my mother, is that I’d made an assumption.

Who says ChatGPT writing is any good?

In most of my interactions with OpenAI’s platform, I've found ChatGPT informative, smart, polite, funny, and occasionally off-base. But I've never marveled at its wordsmithing.

To test my theory, I decided to ask ChatGPT to help me write a movie script. I gave it a very brief synopsis, some characters, and even a little casting, but otherwise, let it write as it saw fit.

A script requires structure, but also, when it comes to dialogue, a real way with words. It should also push the envelope on plot. Could ChatGPT reach the level of a must-read script or a must-see movie?

My brief was for a new Star Trek franchise movie featuring both Captain Picard and Captain Kirk (each played by their originating actors, Patrick Stewart and William Shatner, respectively). The plot would revolve around them time traveling to meet each other and then delivering dilithium crystals to 2023 to be used as a new global energy source. This would set in motion a climate change reversal (in a twist, their actions would enable the creation of The Federation, which means they’re not changing the timeline, just reinforcing it, but I digress). I left all other casting, plot, and action decisions to ChatGPT.

I have to say, ChatGPT totally gets how to write a script with most of the necessary, if skeletal, screen direction. It also did a passable replication of Kirk and Picard’s banter (last seen in the first Star Trek: Generations ). Here’s a tiny taste:

KIRK: What's going on here, Picard?

PICARD: I'm not sure, Kirk. We're investigating a space anomaly when you suddenly appeared.

KIRK: Anomaly? That's one way to describe it.

This Computer read all the blogs

The other thing that became clear is that ChatGPT had already absorbed all Trek lore from both the original series and Star Trek: The Next Generation . Its script quickly employed familiar tropes and characters, including the omniscient Q (played by John de Lancie ) who sets in motion the quest to save Earth.

It cast Emma Stone as a scientist and later added Idris Elba .

The problem with the first draft was that it was so short it lacked a real second and third act. It seemed to leap from the premise to the conclusion as if it was in a race to get to the end credits.

This was my first indication that writing with ChatGPT is not a case of telling the AI bot what you want and then letting it write the entire thing. Our first script felt like the rough draft you might get from a first-year film student.

I asked ChatGPT to expand the script, add more characters from any of the original two series, and throw in a roadblock in the form of terrorists who try to steal the dilithium crystals before Kirk and Picard can complete their mission.

First, ChatGPT seemed to lose interest and delivered half the script. When prompted, it apologized and spat out the rest. This time, the two captains failed. What kind of Star Trek movie is this? I thought.

I asked ChatGPT to rewrite with the twist of Q taking the captains out of time so they can go back to five minutes before terrorists blow up half the crystals and make it impossible for them to complete their mission.

Running out of steam

At this point, ChatGPT seemed to forget it was writing a movie script and just delivered paragraphs of dialogue-free text describing the action. It felt rushed, as if ChatGPT was bored with this exercise and just wanted it to be done.

While I don’t want to post the script in its entirety for fear of unintended copyright infringement, here’s an excerpt from the rushed conclusion:

Together, Kirk, Picard, Emma Stone's character, and the Starfleet officers work to install the dilithium crystals in power plants all over the world, with the ultimate goal of ending the world's dependence on fossil fuels and averting the catastrophic events that would have led to Earth's demise.

As they work, Kirk and Picard find themselves in a strange new world, one where they are surrounded by strange technology and unfamiliar customs. They have to navigate 21st-century New York City, blending in with the locals and adapting to a world that is vastly different from the one they know.

Ultimately, I didn’t end up with a usable script, which was a relief.

It’s not just that ChatGPT isn’t much of a writer, it also lacks the energy and determination to create content at scale. ChatGPT has no burning ambition to be an author – it has no ambition at all. Someone who wants to write a novel or screenplay can’t simply run out of steam . Even as a collaborator, ChatGPT is lacking. Its prose and ideas deteriorated in quality and maturity. I could sense that it had run out of ideas, which is why it kept trying to wrap up the story early.

This is not the profile of a future, great author.

I have a feeling that whatever ChatGPT is helping people publish is mostly, well, garbage, and that human authors and screenwriters are safe, at least for now.

A 38-year industry veteran and award-winning journalist , Lance has covered technology since PCs were the size of suitcases and “on line” meant “waiting.” He’s a former Lifewire Editor-in-Chief, Mashable Editor-in-Chief, and, before that, Editor in Chief of PCMag.com and Senior Vice President of Content for Ziff Davis, Inc. He also wrote a popular, weekly tech column for Medium called The Upgrade.

Lance Ulanoff makes frequent appearances on national, international, and local news programs including Live with Kelly and Ryan, the Today Show , Good Morning America, CNBC, CNN, and the BBC. 

OpenAI just gave artists access to Sora and proved the AI video tool is weirder and more powerful than we thought

How to jailbreak ChatGPT

The Galaxy Z Fold 5 and most of Samsung's best phones and Tabs get Live Translate and more Galaxy AI features

Most Popular

By Demi Williams March 26, 2024

By John Loeffler March 26, 2024

By Chiara Castro March 26, 2024

By Steve Clark March 26, 2024

By Becky Scarrott March 26, 2024

By Tom Power March 26, 2024

By Carrie Marshall March 26, 2024

By Dashiell Wood March 26, 2024

By Leon Poultney March 26, 2024

By Sead Fadilpašić March 26, 2024

• 2 Netflix's Succession-esque new show, A Man in Full, gets its first mysterious trailer
• 3 Best Buy launches massive March Madness TV sale - up to $900 off Samsung, LG and TLC
• 4 How to jailbreak ChatGPT
• 5 Obscure Chinese tablet maker quietly unveiled a tablet with a sought-after feature no other tablet vendor dare launch — a 4K display that not even Apple, Google or Samsung can match
• 2 Another driver update, another set of huge performance boosts for free, as Intel Arc GPUs keep getting better
• 3 1200TB SSD modules are in the pipeline thanks to Pure Storage — but you definitely won't be able to plug one in your workstation PC and it will be shockingly expensive
• 4 Obscure Chinese tablet maker quietly unveiled a tablet with a sought-after feature no other tablet vendor dare launch — a 4K display that not even Apple, Google or Samsung can match
• 5 Windows 11 is forcing users to upgrade Mail app to new Outlook client which comes with a nasty addition – adverts

Write movie or TV show reviews

ChatGPT is an advanced language model that can be utilized to write movie or TV show reviews efficiently. With ChatGPT, you can generate reviews that are informative, engaging, and tailored to your audience's preferences. Whether you're a professional reviewer, a blogger, or just someone who enjoys sharing their thoughts on films and shows, ChatGPT can help you produce high-quality content quickly and easily. The key is to give ChatGPT clear instructions and to provide it with as much relevant information as possible.

Copy a prompt, replace placeholders with relevant text, and paste it at Sintra Chat in the right, bottom corner for an efficient and streamlined experience.

"Kindly compose an exhaustive and insightful [POSITIVE/NEGATIVE] critique of the [MOVIE/TV SHOW] titled [TITLE], incorporating a comprehensive analysis of the plot, characterization, cinematography, soundtrack, and other essential components. The review should be [LENGTH] words long, tailored to engage and inform the readership of my [BLOG/WEBSITE/NEWSPAPER]. Please ensure that the review employs a balanced perspective, featuring both the strengths and potential areas of improvement in the production. Additionally, consider the target demographic, the cultural context, and the contemporary relevance of the [MOVIE/TV SHOW] in your assessment."

Prompt #1 example

Prompt #1 output example.

"Could you write a review for the [GENRE] [MOVIE/TV SHOW] [TITLE]? I would like it to focus on the [PLOT/ACTING/DIRECTING] and be [ENTERTAINING/INFORMATIVE] for my readers."

Prompt #2 example

Prompt #2 output example.

"I was wondering if you could write a [LENGTH] review of the [MOVIE/TV SHOW] [TITLE]. I'd like it to touch on the themes of the [FILM/SHOW] and also include your personal [OPINION/ANALYSIS] on it."

Prompt #3 example

Prompt #3 output example.

"Can you write a [FUNNY/SARCASTIC/SERIOUS] review for [MOVIE/TV SHOW] [TITLE]? I need it for my [USED WHERE?] and would love it if you could make it [ENGAGING/CONTROVERSIAL] for the audience."

Prompt #4 example

Prompt #4 output example.

"Please write a [COMPREHENSIVE/BRIEF] review for the [MOVIE/TV SHOW] [TITLE]. It would be great if you could include [SPOILER-FREE/SPOILERS] [SUMMARY/ANALYSIS] of the [FILM/SHOW] and also mention the [CINEMATOGRAPHY/SOUNDTRACK/VISUAL EFFECTS] if possible."

Prompt #5 example

Prompt #5 output example, rate this prompt.

You need to buy the Sintra Prompt Pack or Sintra Plus in order to unlock rest of these Prompts.

Automate Your Work with Bots

Follow these guidelines to maximize your experience and unlock the full potential of your conversations with Sintra Chat .

Be specific and clear in your prompts: When asking ChatGPT to write a review, make sure to provide it with as much relevant information as possible, such as the genre, the main characters, the plot, and any key themes or motifs.

Use keywords to guide ChatGPT: Use specific terms to indicate the tone, style, or perspective you want your review to take. For example, if you want a critical review, use words like "flaws" or "weaknesses" in your prompt.

Edit and refine the output: ChatGPT can generate a review quickly, but it may not always be perfect. Take the time to read through the output, make any necessary corrections or adjustments, and add your own personal touch to the final product.

You need to buy the Sintra Prompt Pack or Sintra Plus in order to see these Prompt Tips.

Similar Prompts

Discover related prompts to expand your productivity. Seamlessly connecting with ChatGPT for endless conversation possibilities.

Drafting social media bios

Generating error log reports, generating leads for sales team.

How-To Geek

How to use chatgpt to transform writing into another format.

You can easily convert stories, scripts, and other documents into new formats with a little AI assistance.

Quick Links

Getting your text into chatgpt, working in chunks and prompting chatgpt, example 1: turning a blog post into a youtube script, example 2: changing a technical document into a popular article, example 3: turning a short story into a movie script, what to watch out for.

While most people think of ChatGPT as a way to generate new text, one of its most powerful abilities is to transform existing text into another format. Whether this is text that you have written, or text from another source.

The first step in transforming your written content with ChatGPT is to input your original text. This process is straightforward. When prompted, you simply copy and paste your text into the text field.

Keep in mind that ChatGPT is not a mind reader. It uses patterns in the data to generate responses based on the input it's been given. The better your input, the better the output.

Related: What Is ChatGPT Plus?

That being said, I have copied some pretty broken text into ChatGPT and the results were great. For example, copying the entire auto-transcribed chat history of a Microsoft Teams Meeting into ChatGPT and having it write a concise meeting report works surprisingly well.

ChatGPT can only process a certain amount of "tokens" at a time. If your content exceeds this limit, you need to break it down into smaller chunks. ChatGPT will let you know if a prompt was too long, but I've used a method where I prompt ChatGPT with something like "I'm going to give you text in multiple chunks, don't do anything with it, just read it for now." and then paste in the text in multiple parts.

Related: Does ChatGPT Have an App?

Also, the way you prompt ChatGPT matters. If you want to transform your text into a different format, be clear about your intentions. For example, if you want to convert a blog post into a YouTube script, you might preface your text with, "Please convert the following blog post into a script suitable for a YouTube video."

Hopefully, that all makes sense, but we're going to walk through a few practical examples to demonstrate exactly how this works.

Let's take one of yours truly's most popular articles Why Don't We Have 128-Bit Computers Yet? as an example. First, here's the prompt:

Please convert the following blog post into a friendly script suitable for a YouTube video:

Then copy all the text from the article into the prompt after the colon before submitting it.

Now submit the prompt.

ChatGPT will transform the content accordingly, ensuring it's engaging, casual, and interactive to suit the YouTube video format. Remember to revise the output to make sure it includes a clear introduction, body, and conclusion, as well as calls-to-action and engagement prompts typical of YouTube content.

How well does this work? Well, I host a small YouTube channel , and for the past few months I've been using ChatGPT to convert the blog articles each video is based on into a YouTube script format. This is exactly what I had been doing by hand before, except now it takes seconds rather than an hour or two of my time.

As with the other examples you'll see below, a major advantage of having ChatGPT transform text rather than generate it, is that you don't have to worry about it making stuff up that wasn't in the original text. You still need to quality-control the transformed text , but I have yet to encounter a situation where ChatGPT added anything into my scripts that were not in the original text.

Technical documents often involve jargon and complexity that may not be accessible to a general audience. Here, ChatGPT can help.

Prompt ChatGPT as follows:

Please convert the following technical document into a popular article accessible to the general public, with no background in the field:

Now we need some highly-technical information. Why not none other than Albert Einstein? I don't know about you, but I definitely don't have the smarts to understand Einstein's work, so why not try it with one of his papers? Specifically, On the Electrodynamics of Moving Bodies , the 1905 paper that made him famous, where he outlined his Theory of Relativity. You might have heard of that one.

The paper is 24 pages long, so we'll just put a section into ChatGPT for this exercise.

If you're a ChatGPT Plus subscriber, you can make use of the beta plugins store , which includes ChatWithPDF , a plugin that lets you load a PDF and then interact with it using ChatGPT. This may be a more efficient way to get complex technical PDFs into the Chatbot.

The resulting output should be a reader-friendly article that conveys the essence of the technical document in simpler terms. Remember that you can prompt ChatGPT to write text at a particular level, such as a specific grade level in school.

With ChatGPT, you can even turn a short story into a movie script. Input your short story and prompt the model like so:

Please convert the following short story into a movie script, maintaining the essence of the characters and plot.

If we head over to Project Gutenberg , there are many books that are public domain in the USA and many other parts of the world. Its a worthy project that relies on donations, so while you're visiting and you like what they do, it never hurts to give some support!

For this exercise, we're going with the ever-dependable Fairy Tales of Hans Christian Anderson . Specifically, The Emperor's New Suit.

Don't forget that you can be very specific in your prompt, asking ChatGPT to alter the tone or transform the story somehow. You can also specify what sort of script format you want. For example, a spec script or a shooting script.

While ChatGPT is unlikely to produce something of final usable quality right off the bat, it's much easier to edit a script than format and write one from scratch. It's a great way to extract the parts of the story relevant to the script, such as separating dialogue from inner thoughts, or descriptions of locations.

While ChatGPT is a powerful tool, it isn't infallible. It can sometimes produce errors or generate responses that aren't entirely accurate . Be prepared to review and revise the output. It's also important to remember that while ChatGPT can simplify and convert text, it doesn't inherently understand context.

Use the output of ChatGPT as a first draft and then refine it, using your human judgment to ensure accuracy, context, and quality. Consider ChatGPT a writing assistant rather than a replacement for human creativity and nuance.

Related: 8 Surprising Things You Can Do With ChatGPT

ChatGPT offers exciting possibilities for content repurposing, automating some of the work of transforming and simplifying text. While it doesn't replace the human touch, it makes writing more efficient and interesting. This way you can spend more time being creative, and less time doing simple drudge work.

How to Write an AI Logline for a Movie Using ChatGPT or Jasper

Key Takeaways:

• Decide on the parameters of your logline (the main character, inciting incident, objective and antagonistic force).
• Choose an AI writing program and open a new document.
• Use my AI logline prompt (see below).
• Rerun the prompt if the first output isn’t great.
• Tweak the logline to make it your own!

Click here to go directly to the steps!

Artificial Intelligence (AI) has already disrupted many industries, and screenwriting and novel writing are no exceptions.

The traditional process of writing movie loglines tasks the writer with distilling their entire story into a single sentence, and as anyone who’s ever tried it knows, it can be a challenge. AI content generators are now being used to help writers create fantastic loglines for their movies and books.

As a novelist , screenwriter , and filmmaker myself, I know how hard writing can be. I’ve been trying out different AI writing programs to see how they can be best used for creatives, and one use that stood out to me was the writing of loglines.

In this article, we will discuss how to use artificial intelligence writing programs (like ChatGPT , Jasper AI , or Sudowrite ) to help you write a creative logline for your next creative project!

Neil Chase Film is supported by its readers. When you purchase through links on our site, we may earn an affiliate commission. Thank you for your support!

What is a Logline?

A logline is a brief summary of a movie, short film , or book that tells the reader the plot and the central conflict.

It’s usually one or two sentences long, and it’s a great way to get a quick sense of what a story is about. It should be easy to understand and make the reader want to know more about the story.

Writers often use a logline to pitch their ideas to publishers or producers. It is also a valuable tool for marketing and advertising purposes.

In short, a logline is a concise way to summarize a complex story in just a few words.

How do I Write a Logline?

Overall, my best tips for writing a logline are:

• Keep your logline short and to the point
• Brainstorm your best movie ideas before you write the logline!
• Think about the key ingredients of the story elements of your book or movie before writing the logline
• Focus on the main conflict in your story (the central problem that moves the plot forward)
• Don’t use character names in your logline
• Don’t give away the entire script or the whole movie!
• Avoid naming similar books or movies in the logline

Keep the following logline formula in mind as you use AI to help you write a logline:

When INCITING INCIDENT , a PROTAGONIST must OBJECTIVE despite an ANTAGONISTIC FORCE .

If you want more assistance with writing a logline the old-fashioned way (with no AI help!), check out my article on writing a logline for more information. If you are looking for examples of effective movie loglines, check out this article .

How to Use AI to Create a Logline

Now that you know what a logline is and what an AI writing assistant can do, let’s look at how AI can help you write a great logline.

Before we start, please note that I’m using the word “help”!

Artificial intelligence is a beneficial tool but does not replace the human writer. You will still need to understand story structure , character development, and the idea of conflict to write a great logline.

With that said, let’s look at how to use AI to help you quickly and easily write a movie or book logline!

1: Decide on the parameters of your logline

The first step to creating a logline for a story is to decide on the parameters of your story.

A good logline distills the essential  story elements  of your screenplay –  protagonist(s), antagonistic force ,  inciting incident , and objective – into a clear and concise teaser.

Reread your story or screenplay and make sure that you can specify the following aspects:

• Protagonist(s) – The story’s main character(s).
• Inciting Incident – The event that sets the protagonist(s) on their journey. This is the first turning point, where the main character’s ordinary world upends.
• Objective – The main goal of the protagonist(s).
• Antagonistic force – The character, force, or obstacle preventing the protagonist(s) from reaching the objective.

Try to add as much detail as possible about each aspect of your story.

Once you have written down these aspects of your story, you can start writing your logline!

Let’s look at an example from a famous movie (The Wizard of Oz) :

• Protagonist: lonely Kansas farm girl
• Inciting Incident: a twister takes her to a magical land
• Objective: find a wizard who has the power to send her home
• Antagonistic Force: a dangerous journey

2: Open a new document for your AI logline

This step is where you’ll need to sign up for an AI writing program. While I’ve tried quite a few, the two I recommend to fiction writers most are Jasper and Sudowrite .

Jasper is my favorite AI writing tool overall, if you are looking for a multi-purpose tool that is mainly going to help you with marketing tasks.

If, however, you are looking primarily for assistance with creative writing, such as short stories , novels and screenplays, Sudowrite is your best bet!

Try out Jasper if you are looking for a multi-purpose AI writing tool that can help with both marketing and creative tasks.

Unlike Jasper, Sudowrite is a specialized AI writing tool for creative writers! It’s best if all you want AI to help you with is stories and screenplays.

If you are using Jasper AI:

In Jasper, you’ll want to click on Templates, Documents, and “Freeform With Any Template.” Or, you can use “Jasper Chat”, which works much like ChatGPT.

3: Use my prompt to generate your logline

In your opened document, copy and paste the following prompt. Make sure to type in your own parameters where it says, “state yours here.”

<write a logline for the following parameters: main character – state yours here, inciting incident – state yours here, objective – state yours here, antagonistic force – state yours here>

After you enter your own parameters, put your cursor after the final > and press “control J.”

Here’s what happened when I used this prompt in Jasper (the part in the red box was what I gave as a prompt, and the logline below was what Jasper generated for me):

Now, this logline that Jasper generated is not great. So, let’s go on to step 4!

4: Try rerunning the AI prompt

Artificial Intelligence is far from perfect. You may need to adjust your parameters if the logline you get is not quite what you are looking for.

For example, you may need to add extra information about your protagonist (it may give a better logline if you say a “young cocky hockey player from Norway” than just a “hockey player”).

Or, you may need to rerun the AI program. It will often give slightly different loglines each time that you run the command, and you will likely prefer one option to the others.

When I re-ran the Jasper command, I liked the third logline the best (the one right under the red box)!

5: Tweak the logline to make it your own!

Remember that AI is just an assistant to you, the human writer! Please ensure that you use your creative talents and skills to make the logline the best it can be.

Ensure that you add details or adjust the meaning of the logline so that it is true to the story you are writing it for.

I believe that this logline generation method can help make the process easier and faster, but you should not let AI do all the work for you!

In the end, I moved the elements around a bit and went with this logline:

After a twister carries her to a magical land, a lonely Kansas farm girl embarks on a dangerous journey to find a wizard with the power to send her home.

How to Use Sudowrite to Create a Logline

Another AI software you can try is Sudowrite . Sudowrite is a specialty AI writing tool made just for creative writers, such as novelists and screenwriters !

Sudowrite is a fantastic AI that can help you generate AI screenplays and novels and can also help you write a logline! Don’t forget to use proper screenwriting software to write the rest of your script!

Here’s what I got from Sudowrite when I used the same logline prompt as above:

I think that’s a pretty good logline too! I do love that Sudowrite is more specialized for creative writing – there’s a lot you can do with it, way more than just loglines!

How to Use ChatGPT to Write a Logline

Here’s the output I got when I asked ChatGPT to write me an AI logline for the Wizard of Oz. It’s pretty good, but would benefit from some human tweaking!

The nice thing about ChatGPT is that you can ask the program to rewrite the logline in different ways.

Look what happens when I ask the program to rewrite the above logline with the prompt “write this more powerfully”. It is a fantastic logline!

What AI programs can you use?

As noted above, I like to use Jasper for writing loglines. Let’s take a closer look at both Jasper and Sudowrite.

• Jasper is awesome at generating loglines, as shown above.
• Has a free 5-day trial.
• Jasper has various pricing levels, starting at $39 per month.
• Great for writing loglines, generating story ideas, characters, and settings.

• The free plan allows you to generate 4k words, so you see if you like it!
• Write in almost any language (will match the language of your inputs).
• The Hobby/Student Plan includes up to 30k words generated per month and is only $10/month!
• Great for helping generate story ideas.
• Sudowrite helps with rich vocabulary and descriptions too (among many other things)!

Final Thoughts

Although AI programs are not perfect, they can be a great tool to help you develop your movie or book logline.

I hope the steps above help you write a fantastic logline for your next story!

Interested in the intersection of AI and creativity? Check out these other interesting articles!

5+ Best AI Voice Generator Tools: Ranked & Reviewed

Artificial Intelligence In Film: Impact & Influence

How to Turn Text to Video Using AI [Easy Videos!]

Filmmaker, Author, Actor and Story Consultant

Neil Chase is an award-winning, produced screenwriter, independent filmmaker, professional actor, and author of the horror-western novel Iron Dogs. His latest feature film is an apocalyptic thriller called Spin The Wheel.

Neil has been featured on Celtx, No Film School, Script Revolution, Raindance, The Write Practice, Lifewire, and MSN.com, and his work has won awards from Script Summit, ScreamFest, FilmQuest and Cinequest (among others).

Neil believes that all writers have the potential to create great work. His passion is helping writers find their voice and develop their skills so that they can create stories that are entertaining and meaningful. If you’re ready to take your writing to the next level, he's here to help!

Similar Posts

The 35+ Best Film Festivals in the World [2024]

Synthesia.io Review: A Powerful AI Video Generator [2024]

5+ Best Topaz Video Enhance AI Alternatives for Upscaling [2024]

Top 11 Best LED Filming Lights for Filmmakers [in 2024]

What is a Logline? 7 Tips and Free Template for Writers!

The 10+ Best Screenplay Competitions for Screenwriters [2024]

• Pingback: How the Hollywood Writers' Strike Could Accelerate AI - News Leaflets
• Pingback: How the Hollywood Writers' Strike Could Accelerate AI - Techno Blender

Leave a Reply Cancel reply

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

• Privacy Overview
• Strictly Necessary Cookies

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.

Strictly Necessary Cookie should be enabled at all times so that we can save your preferences for cookie settings.

If you disable this cookie, we will not be able to save your preferences. This means that every time you visit this website you will need to enable or disable cookies again.

ChatGPT: Everything you need to know about the AI-powered chatbot

ChatGPT, OpenAI’s text-generating AI chatbot, has taken the world by storm. What started as a tool to hyper-charge productivity through writing essays and code with short text prompts has evolved into a behemoth used by more than 92% of Fortune 500 companies for more wide-ranging needs. And that growth has propelled OpenAI itself into becoming one of the most-hyped companies in recent memory, even if CEO and co-founder Sam Altman’s firing and swift return  raised concerns about its direction and opened the door for competitors.

What does that mean for OpenAI, ChatGPT and its other ambitions? The fallout is still settling, but it might empower competitors like Meta and its LLaMA family of large language models , or help other AI startups get attention and funding as the industry watches OpenAI implode and put itself back together.

While there is a more… nefarious side to ChatGPT, it’s clear that AI tools are not going away anytime soon. Since its initial launch nearly a year ago, ChatGPT has hit 100 million weekly active users , and OpenAI is heavily investing in it.

Prior to the leadership chaos, on November 6, OpenAI held its first developer conference: OpenAI DevDay. During the conference, it announced a slew of updates coming to GPT, including GPT-4 Turbo (a super-charged version of GPT-4 , its latest language-writing model) and a multimodal API . OpenAI also unveiled the GPT store , where users could create and monetize their own custom versions of GPT. Though the launch was delayed in December , it officially launched in January.

GPT-4, which can write more naturally and fluently than previous models, remains largely exclusive to paying ChatGPT users. But you can access GPT-4 for free through Microsoft’s Bing Chat in Microsoft Edge, Google Chrome and Safari web browsers. Beyond GPT-4 and OpenAI DevDay announcements, OpenAI recently connected ChatGPT to the internet for all users. And with the integration of DALL-E 3, users are also able to generate both text prompts and images right in ChatGPT. 

Here’s a timeline of ChatGPT product updates and releases, starting with the latest, which we’ve been updating throughout the year. And if you have any other questions, check out our ChatGPT FAQ here .

Timeline of the most recent ChatGPT updates

February 2024, january 2024, december 2023.

• November 2023 

October 2023

September 2023, august 2023, february 2023, january 2023, december 2022, november 2022.

• ChatGPT FAQs

The New York Times responds to OpenAI’s claims that it “hacked” ChatGPT for its copyright lawsuit

In a court filing opposing OpenAI’s motion to dismiss The New York Times’ lawsuit alleging copyright infringement, the newspaper asserted that “OpenAI’s attention-grabbing claim that The Times ‘hacked’ its products is as irrelevant as it is false.” The New York Times also claimed that some users of ChatGPT used the tool to bypass its paywalls.

OpenAI VP doesn’t say whether artists should be paid for training data

At a SXSW 2024 panel, Peter Deng, OpenAI’s VP of consumer product dodged a question on whether artists whose work was used to train generative AI models should be compensated . While OpenAI lets artists “opt out” of and remove their work from the datasets that the company uses to train its image-generating models, some artists have described the tool as onerous.

A new report estimates that ChatGPT uses more than half a million kilowatt-hours of electricity per day

ChatGPT’s environmental impact appears to be massive. According to a report from The New Yorker , ChatGPT uses an estimated 17,000 times the amount of electricity than the average U.S. household to respond to roughly 200 million requests each day.

ChatGPT can now read its answers aloud

OpenAI released a new Read Aloud feature for the web version of ChatGPT as well as the iOS and Android apps. The feature allows ChatGPT to read its responses to queries in one of five voice options and can speak 37 languages, according to the company. Read aloud is available on both GPT-4 and GPT-3.5 models.

ChatGPT can now read responses to you. On iOS or Android, tap and hold the message and then tap “Read Aloud”. We’ve also started rolling on web – click the "Read Aloud" button below the message. pic.twitter.com/KevIkgAFbG — OpenAI (@OpenAI) March 4, 2024

OpenAI partners with Dublin City Council to use GPT-4 for tourism

As part of a new partnership with OpenAI, the Dublin City Council will use GPT-4 to craft personalized itineraries for travelers, including recommendations of unique and cultural destinations, in an effort to support tourism across Europe.

A law firm used ChatGPT to justify a six-figure bill for legal services

New York-based law firm Cuddy Law was criticized by a judge for using ChatGPT to calculate their hourly billing rate . The firm submitted a $113,500 bill to the court, which was then halved by District Judge Paul Engelmayer, who called the figure “well above” reasonable demands.

ChatGPT experienced a bizarre bug for several hours

ChatGPT users found that ChatGPT was giving nonsensical answers for several hours , prompting OpenAI to investigate the issue. Incidents varied from repetitive phrases to confusing and incorrect answers to queries. The issue was resolved by OpenAI the following morning.

Match Group announced deal with OpenAI with a press release co-written by ChatGPT

The dating app giant home to Tinder, Match and OkCupid announced an enterprise agreement with OpenAI in an enthusiastic press release written with the help of ChatGPT . The AI tech will be used to help employees with work-related tasks and come as part of Match’s $20 million-plus bet on AI in 2024.

ChatGPT will now remember — and forget — things you tell it to

As part of a test, OpenAI began rolling out new “memory” controls for a small portion of ChatGPT free and paid users, with a broader rollout to follow. The controls let you tell ChatGPT explicitly to remember something, see what it remembers or turn off its memory altogether. Note that deleting a chat from chat history won’t erase ChatGPT’s or a custom GPT’s memories — you must delete the memory itself.

We’re testing ChatGPT's ability to remember things you discuss to make future chats more helpful. This feature is being rolled out to a small portion of Free and Plus users, and it's easy to turn on or off. https://t.co/1Tv355oa7V pic.twitter.com/BsFinBSTbs — OpenAI (@OpenAI) February 13, 2024

OpenAI begins rolling out “Temporary Chat” feature

Initially limited to a small subset of free and subscription users, Temporary Chat lets you have a dialogue with a blank slate. With Temporary Chat, ChatGPT won’t be aware of previous conversations or access memories but will follow custom instructions if they’re enabled.

But, OpenAI says it may keep a copy of Temporary Chat conversations for up to 30 days for “safety reasons.”

Use temporary chat for conversations in which you don’t want to use memory or appear in history. pic.twitter.com/H1U82zoXyC — OpenAI (@OpenAI) February 13, 2024

ChatGPT users can now invoke GPTs directly in chats

Paid users of ChatGPT can now bring GPTs into a conversation by typing “@” and selecting a GPT from the list. The chosen GPT will have an understanding of the full conversation, and different GPTs can be “tagged in” for different use cases and needs.

You can now bring GPTs into any conversation in ChatGPT – simply type @ and select the GPT. This allows you to add relevant GPTs with the full context of the conversation. pic.twitter.com/Pjn5uIy9NF — OpenAI (@OpenAI) January 30, 2024

ChatGPT is reportedly leaking usernames and passwords from users’ private conversations

Screenshots provided to Ars Technica found that ChatGPT is potentially leaking unpublished research papers, login credentials and private information from its users. An OpenAI representative told Ars Technica that the company was investigating the report.

ChatGPT is violating Europe’s privacy laws, Italian DPA tells OpenAI

OpenAI has been told it’s suspected of violating European Union privacy , following a multi-month investigation of ChatGPT by Italy’s data protection authority. Details of the draft findings haven’t been disclosed, but in a response, OpenAI said: “We want our AI to learn about the world, not about private individuals.”

OpenAI partners with Common Sense Media to collaborate on AI guidelines

In an effort to win the trust of parents and policymakers, OpenAI announced it’s partnering with Common Sense Media to collaborate on AI guidelines and education materials for parents, educators and young adults. The organization works to identify and minimize tech harms to young people and previously flagged ChatGPT as lacking in transparency and privacy .

OpenAI responds to Congressional Black Caucus about lack of diversity on its board

After a letter from the Congressional Black Caucus questioned the lack of diversity in OpenAI’s board, the company responded . The response, signed by CEO Sam Altman and Chairman of the Board Bret Taylor, said building a complete and diverse board was one of the company’s top priorities and that it was working with an executive search firm to assist it in finding talent. 

OpenAI drops prices and fixes ‘lazy’ GPT-4 that refused to work

In a blog post , OpenAI announced price drops for GPT-3.5’s API, with input prices dropping to 50% and output by 25%, to $0.0005 per thousand tokens in, and $0.0015 per thousand tokens out. GPT-4 Turbo also got a new preview model for API use, which includes an interesting fix that aims to reduce “laziness” that users have experienced.

Expanding the platform for @OpenAIDevs : new generation of embedding models, updated GPT-4 Turbo, and lower pricing on GPT-3.5 Turbo. https://t.co/7wzCLwB1ax — OpenAI (@OpenAI) January 25, 2024

OpenAI bans developer of a bot impersonating a presidential candidate

OpenAI has suspended AI startup Delphi, which developed a bot impersonating Rep. Dean Phillips (D-Minn.) to help bolster his presidential campaign. The ban comes just weeks after OpenAI published a plan to combat election misinformation, which listed “chatbots impersonating candidates” as against its policy.

OpenAI announces partnership with Arizona State University

Beginning in February, Arizona State University will have full access to ChatGPT’s Enterprise tier , which the university plans to use to build a personalized AI tutor, develop AI avatars, bolster their prompt engineering course and more. It marks OpenAI’s first partnership with a higher education institution.

Winner of a literary prize reveals around 5% her novel was written by ChatGPT

After receiving the prestigious Akutagawa Prize for her novel The Tokyo Tower of Sympathy, author Rie Kudan admitted that around 5% of the book quoted ChatGPT-generated sentences “verbatim.” Interestingly enough, the novel revolves around a futuristic world with a pervasive presence of AI.

Sam Altman teases video capabilities for ChatGPT and the release of GPT-5

In a conversation with Bill Gates on the Unconfuse Me podcast, Sam Altman confirmed an upcoming release of GPT-5 that will be “fully multimodal with speech, image, code, and video support.” Altman said users can expect to see GPT-5 drop sometime in 2024.

OpenAI announces team to build ‘crowdsourced’ governance ideas into its models

OpenAI is forming a Collective Alignment team of researchers and engineers to create a system for collecting and “encoding” public input on its models’ behaviors into OpenAI products and services. This comes as a part of OpenAI’s public program to award grants to fund experiments in setting up a “democratic process” for determining the rules AI systems follow.

OpenAI unveils plan to combat election misinformation

In a blog post, OpenAI announced users will not be allowed to build applications for political campaigning and lobbying until the company works out how effective their tools are for “personalized persuasion.”

Users will also be banned from creating chatbots that impersonate candidates or government institutions, and from using OpenAI tools to misrepresent the voting process or otherwise discourage voting.

The company is also testing out a tool that detects DALL-E generated images and will incorporate access to real-time news, with attribution, in ChatGPT.

Snapshot of how we’re preparing for 2024’s worldwide elections: • Working to prevent abuse, including misleading deepfakes • Providing transparency on AI-generated content • Improving access to authoritative voting information https://t.co/qsysYy5l0L — OpenAI (@OpenAI) January 15, 2024

OpenAI changes policy to allow military applications

In an unannounced update to its usage policy , OpenAI removed language previously prohibiting the use of its products for the purposes of “military and warfare.” In an additional statement, OpenAI confirmed that the language was changed in order to accommodate military customers and projects that do not violate their ban on efforts to use their tools to “harm people, develop weapons, for communications surveillance, or to injure others or destroy property.”

ChatGPT subscription aimed at small teams debuts

Aptly called ChatGPT Team , the new plan provides a dedicated workspace for teams of up to 149 people using ChatGPT as well as admin tools for team management. In addition to gaining access to GPT-4, GPT-4 with Vision and DALL-E3, ChatGPT Team lets teams build and share GPTs for their business needs.

OpenAI’s GPT store officially launches

After some back and forth over the last few months, OpenAI’s GPT Store is finally here . The feature lives in a new tab in the ChatGPT web client, and includes a range of GPTs developed both by OpenAI’s partners and the wider dev community.

To access the GPT Store, users must be subscribed to one of OpenAI’s premium ChatGPT plans — ChatGPT Plus, ChatGPT Enterprise or the newly launched ChatGPT Team.

the GPT store is live! https://t.co/AKg1mjlvo2 fun speculation last night about which GPTs will be doing the best by the end of today. — Sam Altman (@sama) January 10, 2024

Developing AI models would be “impossible” without copyrighted materials, OpenAI claims

Following a proposed ban on using news publications and books to train AI chatbots in the U.K., OpenAI submitted a plea to the House of Lords communications and digital committee. OpenAI argued that it would be “impossible” to train AI models without using copyrighted materials, and that they believe copyright law “does not forbid training.”

OpenAI claims The New York Times’ copyright lawsuit is without merit

OpenAI published a public response to The New York Times’s lawsuit against them and Microsoft for allegedly violating copyright law, claiming that the case is without merit.

In the response , OpenAI reiterates its view that training AI models using publicly available data from the web is fair use. It also makes the case that regurgitation is less likely to occur with training data from a single source and places the onus on users to “act responsibly.”

We build AI to empower people, including journalists. Our position on the @nytimes lawsuit: • Training is fair use, but we provide an opt-out • "Regurgitation" is a rare bug we're driving to zero • The New York Times is not telling the full story https://t.co/S6fSaDsfKb — OpenAI (@OpenAI) January 8, 2024

OpenAI’s app store for GPTs planned to launch next week

After being delayed in December , OpenAI plans to launch its GPT Store sometime in the coming week, according to an email viewed by TechCrunch. OpenAI says developers building GPTs will have to review the company’s updated usage policies and GPT brand guidelines to ensure their GPTs are compliant before they’re eligible for listing in the GPT Store. OpenAI’s update notably didn’t include any information on the expected monetization opportunities for developers listing their apps on the storefront.

GPT Store launching next week – OpenAI pic.twitter.com/I6mkZKtgZG — Manish Singh (@refsrc) January 4, 2024

OpenAI moves to shrink regulatory risk in EU around data privacy

In an email, OpenAI detailed an incoming update to its terms, including changing the OpenAI entity providing services to EEA and Swiss residents to OpenAI Ireland Limited. The move appears to be intended to shrink its regulatory risk in the European Union, where the company has been under scrutiny over ChatGPT’s impact on people’s privacy.

Study finds white-collar workers are uneasy about using ChatGPT

A study conducted by professors from Harvard and MIT , which is still under review, looked at how ChatGPT could affect the productivity of more than 750 white-collar workers, as well as their complicated feelings about using the tool. The study found that while ChatGPT was helpful with creative tasks, workers were led to more mistakes with analytical work.

The New York Times sues OpenAI and Microsoft over alleged copyright infringement

In a lawsuit filed in the Federal District Court in Manhattan , The Times argues that millions of its articles were used to train AI models without its consent. The Times is asking for OpenAI and Microsoft to “destroy” models and training data containing offending material and to be held responsible for “billions of dollars in statutory and actual damages.”

OpenAI re-opens ChatGPT Plus subscriptions

After pausing ChatGPT Plus subscriptions in November due to a “surge of usage,” OpenAI CEO Sam Altman announced they have once again enabled sign-ups. The Plus subscription includes access to GPT-4 and GPT-4 Turbo .

we have re-enabled chatgpt plus subscriptions! 🎄 thanks for your patience while we found more gpus. — Sam Altman (@sama) December 13, 2023

OpenAI and Axel Springer partner up for a “real-time” ChatGPT news deal

OpenAI has struck a new deal with Berlin-based news publisher Axel Springer , which owns Business Insider and Politico, to “help provide people with new ways to access quality, real-time news content through our AI tools.” OpenAI will train its generative AI models on the publisher’s content and add recent Axel Springer-published articles to ChatGPT.

Stanford researchers say ChatGPT didn’t cause an influx in cheating in high schools

New research from Stanford University shows that the popularization of chatbots like ChatGPT has not caused an increase in cheating across U.S. high schools. In a survey of more than 40 U.S. high schools, researchers found that cheating rates are similar across the board this year.

ChatGPT users worry the chatbot is experiencing seasonal depression

Starting in November, ChatGPT users have noticed that the chatbot feels “lazier” than normal, citing instances of simpler answers and refusing to complete requested tasks. OpenAI has confirmed that they are aware of this issue , but aren’t sure why it’s happening.

Some users think it plays into the “winter break hypothesis,” which argues that AI is worse in December because it “learned” to do less work over the holidays , while others wonder if the chatbot is simulating seasonal depression .

we've heard all your feedback about GPT4 getting lazier! we haven't updated the model since Nov 11th, and this certainly isn't intentional. model behavior can be unpredictable, and we're looking into fixing it 🫡 — ChatGPT (@ChatGPTapp) December 8, 2023

Judges in the U.K. are now allowed to use ChatGPT in legal rulings

The U.K. Judicial Office issued guidance that permits judges to use ChatGPT, along with other AI tools, to write legal rulings and perform court duties. The guidance lays out ways to responsibly use AI in the courts, including being aware of potential bias and upholding privacy.

OpenAI makes repeating words “forever” a violation of its terms of service after Google DeepMind test

Following an experiment by Google DeepMind researchers that led ChatGPT to repeat portions of its training data, OpenAI has flagged asking ChatGPT to repeat specific words “forever” as a violation of its terms of service .

Lawmakers in Brazil enact an ordinance written by ChatGPT

City lawmakers in Brazil enacted a piece of legislation written entirely by ChatGPT without even knowing. Weeks after the bill was passed, Porto Alegre councilman Ramiro Rosário admitted that he used ChatGPT to write the proposal, and did not tell fellow council members until after the fact.

OpenAI reportedly delays the launch of its GPT store to 2024

According to a memo seen by Axios , OpenAI plans to delay the launch of its highly anticipated GPT store to early 2024. Custom GPTs and the accompanying store was a major announcement at OpenAI’s DevDay conference , with the store expected to open last month.

November 2023

Chatgpts mobile apps top 110m installs and nearly $30m in revenue.

After launching for iOS and Androidin May and July, ChatGPT’s have topped 110 million combined installs and have reached nearly $30 million in consumer spending, according to a market analysis by data.ai.

ChatGPT celebrates one-year anniversary

OpenAI hit a major milestone: one year of ChatGPT . What began as a “low-key research preview” evolved into a powerhouse that changed the AI industry forever. In a post on X , CEO Sam Altman looked back on the night before its launch: “what a year it’s been…”

a year ago tonight we were probably just sitting around the office putting the finishing touches on chatgpt before the next morning’s launch. what a year it’s been… — Sam Altman (@sama) November 30, 2023

Apple and Google avoid naming ChatGPT as their ‘app of the year’

Neither Apple nor Google chose an AI app as its app of the year for 2023, despite the success of ChatGPT’s mobile app, which became the fastest-growing consumer application in history before the record was broken by Meta’s Threads .

An attack from researchers prompts ChatGPT to reveal training data

A test led by researchers at Google DeepMind found that there is a significant amount of privately identifiable information in OpenAI’s LLMs. The test involved asking ChatGPT to repeat the word “poem” forever, among other words, which over time led the chatbot to churn out private information like email addresses and phone numbers.

ChatGPT and other AI chatbots are fueling an increase in phishing emails

According to a new report by SlashNext , there’s been a 1,265% increase in malicious phishing emails since Q4 of 2022. The report alleges that AI tools like ChatGPT are being prominently used by cybercriminals to write compelling and sophisticated phishing emails .

South Africa officials investigate if President Cyril Ramaphosa used ChatGPT to write a speech

Following speculation, social media users fed portions of Ramaphosa’s November 21 speech in Johannesburg through AI detectors , alleging parts of it may have been written with ChatGPT. South African presidency spokesperson Vincent Magwenya refuted the claims, and local officials are investigating.

ChatGPT Voice can be used to replace Siri

Now that OpenAI’s ChatGPT Voice feature is available to all free users, it can be used to replace Siri on an iPhone 15 Pro and Pro Max by configuring the new Action Button. The new feature lets you ask ChatGPT questions and listen to its responses — like a much smarter version of Siri.

Sam Altman returns as CEO

Altman’s return came swiftly , with an “agreement in principle” announced between him and OpenAI’s board that will reinstate him as CEO and restructure the board to include new members, including former U.S. Treasury Secretary Larry Summers . The biggest takeaway for ChatGPT is that the members of the board more focused on the nonprofit side of OpenAI, with the most concerns over the commercialization of its tools, have been pushed to the side .

ChatGPT Voice rolls out to all free users

Even if its leadership is in flux, OpenAI is still releasing updates to ChatGPT . First announced in September and granted to paid users on a rolling basis, the text-to-speech model can create a voice from text prompts and a few seconds of speech samples. OpenAI worked with voice actors to create the five voice options, and you can give it a shot by heading to the settings in your mobile ChatGPT apps and tapping the “headphones” icon.

Sam Altman might return, but it’s complicated

The only constant within OpenAI right now is change, and in a series of interviews, Nadella hedged on earlier reporting that Altman and Brockman were headed to Microsoft .

“Obviously, we want Sam and Greg to have a fantastic home if they’re not going to be in OpenAI,” Nadella said in an interview with CNBC, saying that we was “open” to them settling at Microsoft or returning to OpenAI should the board and employees support the move.

Confirmation Sam Altman will not return as OpenAI’s CEO

A number of investors and OpenAI employees tried to bring back Altman after his sudden firing by the company’s board, but following a weekend of negotiations, it was confirmed that Altman would not return to OpenAI and new leadership would take hold. What this means for ChatGPT’s future, and for the OpenAI Dev Day announcements , remains to be seen.

Sam Altman ousted as OpenAI’s CEO

Sam Altman has been fired from OpenAI . He will leave the company’s board and step down as CEO, with OpenAI’s chief technology officer Mira Murati stepping in as interim CEO. In a blog post from OpenAI, the company writes that the board “no longer has confidence in [Altman’s] ability to continue leading OpenAI.”

In a statement on X , Altman said working at OpenAI “was transformative” for him and “hopefully the world.”

OpenAI explores how ChatGPT can be used in the classroom

OpenAI COO Brad Lightcap revealed at a San Francisco conference that the company will likely create a team to identify ways AI and ChatGPT can be used in education . This announcement comes at a time when ChatGPT is being criticized by educators for encouraging cheating , resulting in bans in certain school districts .

OpenAI pauses new ChatGPT Plus subscriptions due to a “surge of usage”

Following OpenAI’s Dev Day conference , Sam Altman announced the company is putting a pause on new subscriptions for its premium ChatGPT Plus offering. The temporary hold on sign-ups, as well as the demand for ChatGPT Plus’ new features like making custom GPTS , has led to a slew of resellers on eBay .

ChatGPT gets flagged as potentially unsafe for kids

An independent review from Common Sense Media, a nonprofit advocacy group, found that  ChatGPT could potentially be harmful for younger users. ChatGPT got an overall three-star rating in the report, with its lowest ratings relating to transparency, privacy, trust and safety. 

OpenAI blames DDoS attack for ChatGPT outage

OpenAI confirmed that a DDoS attack was behind outages affecting ChatGPT and its developer tools. ChatGPT experienced sporadic outages for about 24 hours, resulting in users being unable to log into or use the service.

OpenAI debuts GPT-4 Turbo

OpenAI unveiled GPT-4 Turbo at its first-ever OpenAI DevDay conference. GPT-4 Turbo comes in two versions: one that’s strictly text-analyzing and another that understands the context of both text and images.

GPT-4 gets a fine-tuning

As opposed to the fine-tuning program for GPT-3.5, the GPT-4 program will involve more oversight and guidance from OpenAI teams, the company says — largely due to technical hurdles.

OpenAI’s GPT Store lets you build (and monetize) your own GPT

Users and developers will soon be able to make their own GPT , with no coding experience required. Anyone building their own GPT will also be able to list it on OpenAI’s marketplace and monetize it in the future.

ChatGPT has 100 million weekly active users

After being released nearly a year ago, ChatGPT has 100 million weekly active users . OpenAI CEO Sam Altman also revealed that over two million developers use the platform, including more than 92% of Fortune 500 companies.

OpenAI launches DALL-E 3 API, new text-to-speech models

DALL-E 3, OpenAI’s text-to-image model , is now available via an API after first coming to ChatGPT-4 and Bing Chat. OpenAI’s newly released text-to-speech API, Audio API, offers six preset voices to choose from and two generative AI model variants.

OpenAI promises to defend business customers against copyright claims

Bowing to peer pressure, OpenAI it will pay legal costs incurred by customers who face lawsuits over IP claims against work generated by an OpenAI tool. The protections seemingly don’t extend to all OpenAI products, like the free and Plus tiers of ChatGPT.

As OpenAI’s multimodal API launches broadly, research shows it’s still flawed

OpenAI announced that GPT-4 with vision will become available alongside the upcoming launch of GPT-4 Turbo API. But some researchers found that the model remains flawed in several significant and problematic ways.

OpenAI launches API, letting developers build ‘assistants’ into their apps

At its OpenAI DevDay, OpenAI announced the Assistants API to help developers build “agent-like experiences” within their apps. Use cases range from a natural language-based data analysis app to a coding assistant or even an AI-powered vacation planner.

ChatGPT app revenue shows no signs of slowing, but it’s not #1

OpenAI’s chatbot app far outpaces all others on mobile devices in terms of downloads, but it’s surprisingly not the top AI app by revenue . Several other AI chatbots, like  “Chat & Ask AI” and “ChatOn — AI Chat Bot Assistant”, are actually making more money than ChatGPT.

ChatGPT tests the ability to upload and analyze files for Plus users

Subscribers to ChatGPT’s Enterprise Plan have reported new beta features, including the ability to upload PDFs to analyze and and ask questions about them directly. The new rollout also makes it so users no longer have to manually select a mode like DALL-E and browsing when using ChatGPT. Instead, users will automatically be switched to models based on the prompt.

ChatGPT officially gets web search

OpenAI has formally launched its internet-browsing feature to ChatGPT, some three weeks after re-introducing the feature in beta after several months in hiatus. The AI chatbot that has historically been limited to data up to September, 2021.

OpenAI integrates DALL-E 3 into ChatGPT

The integration means users don’t have to think so carefully about their text-prompts when asking DALL-E to create an image. Users will also now be able to receive images as part of their text-based queries without having to switch between apps.

Microsoft-affiliated research finds flaws in GPT-4

A Microsoft-affiliated scientific paper looked at the “trustworthiness” — and toxicity — of LLMs, including GPT-4. Because GPT-4 is more likely to follow the instructions of “jailbreaking” prompts, the co-authors claim that GPT-4 can be more easily prompted than other LLMs to spout toxic, biased text .

ChatGPT’s mobile app hits record $4.58M in revenue in September

OpenAI amassed 15.6 million downloads and nearly $4.6 million in gross revenue across its iOS and Android apps worldwide in September. But revenue growth has now begun to slow , according to new data from market intelligence firm Appfigures — dropping from 30% to 20% in September.

ChatGPT can now browse the internet (again)

OpenAI posted on Twitter/X that ChatGPT can now browse the internet and is no longer limited to data before September 2021. The chatbot had a web browsing capability for Plus subscribers back in July , but the feature was taken away after users exploited it to get around paywalls.

ChatGPT can now browse the internet to provide you with current and authoritative information, complete with direct links to sources. It is no longer limited to data before September 2021. pic.twitter.com/pyj8a9HWkB — OpenAI (@OpenAI) September 27, 2023

ChatGPT now has a voice

OpenAI announced that it’s adding a new voice for verbal conversations and image-based smarts to the AI-powered chatbot.

Poland opens an investigation against OpenAI

The Polish authority publically announced it has opened an investigation regarding ChatGPT — accusing the company of a string of breaches of the EU’s General Data Protection Regulation (GDPR).

OpenAI unveils DALL-E 3

The upgraded text-to-image tool, DALL-E 3, uses ChatGPT to help fill in prompts. Subscribers to OpenAI’s premium ChatGPT plans, ChatGPT Plus  and  ChatGPT Enterprise , can type in a request for an image and hone it through conversations with the chatbot — receiving the results directly within the chat app.

Opera GX integrates ChatGPT-powered AI

Powered by OpenAI’s ChatGPT, the AI browser Aria  launched on Opera in May to give users an easier way to search, ask questions and write code. Today, the company announced it is bringing Aria to Opera GX , a version of the flagship Opera browser that is built for gamers.

The new feature allows Opera GX users to interact directly with a browser AI to find the latest gaming news and tips.

OpenAI releases a guide for teachers using ChatGPT in the classroom

OpenAI wants to rehabilitate the system’s image a bit when it comes to education, as ChatGPT has been controversial in the classroom due to plagiarism. OpenAI has offered up a selection of ways to put the chatbot to work in the classroom.

OpenAI launches ChatGPT Enterprise

ChatGPT Enterprise can perform the same tasks as ChatGPT, such as writing emails, drafting essays and debugging computer code. However, the new offering also adds “enterprise-grade” privacy and data analysis capabilities on top of the vanilla ChatGPT, as well as enhanced performance and customization options.

Survey finds relatively few American use ChatGPT

Recent Pew polling suggests the language model isn’t quite as popular or threatening as some would have you think. Ongoing polling by Pew Research shows that although ChatGPT is gaining mindshare, only about 18% of Americans have ever actually used it .

OpenAI brings fine-tuning to GPT-3.5 Turbo

With fine-tuning, companies using GPT-3.5 Turbo through the company’s API can make the model better follow specific instructions. For example, having the model always respond in a given language. Or improving the model’s ability to consistently format responses, as well as hone the “feel” of the model’s output, like its tone, so that it better fits a brand or voice. Most notably, fine-tuning enables OpenAI customers to shorten text prompts to speed up API calls and cut costs.

OpenAI is partnering with Scale AI to allow companies to fine-tune GPT-3.5 . However, it is unclear whether OpenAI is developing an in-house tuning tool that is meant to complement platforms like Scale AI or serve a different purpose altogether.

Fine-tuning costs:

• Training: $0.008 / 1K tokens
• Usage input: $0.012 / 1K tokens
• Usage output: $0.016 / 1K tokens

OpenAI acquires Global Illumination

In OpenAI’s first public acquisition in its seven-year history, the company announced it has acquired Global Illumination, a New York-based startup leveraging AI to build creative tools, infrastructure and digital experiences.

“We’re very excited for the impact they’ll have here at OpenAI,” OpenAI wrote in a brief  post published to its official blog. “The entire team has joined OpenAI to work on our core products including ChatGPT.”

The ‘custom instructions’ feature is extended to free ChatGPT users

OpenAI announced that it’s expanding custom instructions to all users, including those on the free tier of service. The feature allows users to add various preferences and requirements that they want the AI chatbot to consider when responding.

China requires AI apps to obtain an administrative license

Multiple generative AI apps have been removed from Apple’s China App Store ahead of the country’s latest generative AI regulations that are set to take effect August 15.

“As you may know, the government has been tightening regulations associated with deep synthesis technologies (DST) and generative AI services, including ChatGPT. DST must fulfill permitting requirements to operate in China, including securing a license from the Ministry of Industry and Information Technology (MIIT),” Apple said in a letter to OpenCat, a native ChatGPT client. “Based on our review, your app is associated with ChatGPT, which does not have requisite permits to operate in China.”

ChatGPT for Android is now available in the US, India, Bangladesh and Brazil

A few days after putting up a preorder page on Google Play, OpenAI has flipped the switch and  released ChatGPT for Android . The app is now live in a handful of countries.

ChatGPT is coming to Android

ChatGPT is available to “pre-order” for Android users.

The ChatGPT app on Android  looks to be more or less identical to the iOS one in functionality, meaning it gets most if not all of the web-based version’s features. You should be able to sync your conversations and preferences across devices, too — so if you’re iPhone at home and Android at work, no worries.

OpenAI launches customized instructions for ChatGPT

OpenAI launched custom instructions for ChatGPT users , so they don’t have to write the same instruction prompts to the chatbot every time they interact with it.

The company said this feature lets you “share anything you’d like ChatGPT to consider in its response.” For example, a teacher can say they are teaching fourth-grade math or a developer can specify the code language they prefer when asking for suggestions. A person can also specify their family size, so the text-generating AI can give responses about meals, grocery and vacation planning accordingly.

The FTC is reportedly investigating OpenAI

The FTC is reportedly in at least the exploratory phase of investigation over whether OpenAI’s flagship ChatGPT conversational AI made “false, misleading, disparaging or harmful” statements about people.

TechCrunch Reporter Devin Coldewey reports:

This kind of investigation doesn’t just appear out of thin air — the FTC doesn’t look around and say “That looks suspicious.” Generally a lawsuit or formal complaint is brought to their attention and the practices described by it imply that regulations are being ignored. For example, a person may sue a supplement company because the pills made them sick, and the FTC will launch an investigation on the back of that because there’s evidence the company lied about the side effects.

OpenAI announced the general availability of GPT-4

Starting July 6, all existing OpenAI developers “with a history of successful payments” can access GPT-4 . OpenAI plans to open up access to new developers by the end of July.

In the future, OpenAI says that it’ll allow developers to fine-tune GPT-4 and  GPT-3.5 Turbo , one of the original models powering ChatGPT, with their own data, as has long been possible with several of OpenAI’s other text-generating models. That capability should arrive later this year, according to OpenAI.

ChatGPT app can now search the web only on Bing

OpenAI announced that subscribers to ChatGPT Plus can now use a new feature on the app called Browsing , which allows ChatGPT to search Bing for answers to questions.

The Browsing feature can be enabled by heading to the New Features section of the app settings, selecting “GPT-4” in the model switcher and choosing “Browse with Bing” from the drop-down list. Browsing is available on both the iOS and Android ChatGPT apps.

Mercedes is adding ChatGPT to its infotainment system

U.S. owners of Mercedes models that use MBUX will be able to opt into a beta program starting June 16 activating the ChatGPT functionality . This will enable the highly versatile large language model to augment the car’s conversation skills. You can join up simply by telling your car “Hey Mercedes, I want to join the beta program.”

It’s not really clear what for, though.

ChatGPT app is now available on iPad, adds support for Siri and Shortcuts

The new ChatGPT app version brings native iPad support to the app , as well as support for using the chatbot with Siri and Shortcuts. Drag and drop is also now available, allowing users to drag individual messages from ChatGPT into other apps.

On iPad, ChatGPT now runs in full-screen mode, optimized for the tablet’s interface.

Texas judge orders all AI-generated content must be declared and checked

The Texas federal judge has added a requirement that any attorney appearing in his court must attest that “no portion of the filing was drafted by generative artificial intelligence,” or if it was, that it was checked “by a human being.”

ChatGPT app expanded to more than 30 countries

The list of new countries includes Algeria, Argentina, Azerbaijan, Bolivia, Brazil, Canada, Chile, Costa Rica, Ecuador, Estonia, Ghana, India, Iraq, Israel, Japan, Jordan, Kazakhstan, Kuwait, Lebanon, Lithuania, Mauritania, Mauritius, Mexico, Morocco, Namibia, Nauru, Oman, Pakistan, Peru, Poland, Qatar, Slovenia, Tunisia and the United Arab Emirates.

ChatGPT app is now available in 11 more countries

OpenAI announced in a tweet that the ChatGPT mobile app is now available on iOS in the U.S., Europe, South Korea and New Zealand, and soon more will be able to download the app from the app store. In just six days, the app topped 500,000 downloads .

The ChatGPT app for iOS is now available to users in 11 more countries — Albania, Croatia, France, Germany, Ireland, Jamaica, Korea, New Zealand, Nicaragua, Nigeria, and the UK. More to come soon! — OpenAI (@OpenAI) May 24, 2023

OpenAI launches a ChatGPT app for iOS

ChatGPT is officially going mobile . The new ChatGPT app will be free to use, free from ads and will allow for voice input, the company says, but will initially be limited to U.S. users at launch.

When using the mobile version of ChatGPT, the app will sync your history across devices — meaning it will know what you’ve previously searched for via its web interface, and make that accessible to you. The app is also integrated with  Whisper , OpenAI’s open source speech recognition system, to allow for voice input.

Hackers are using ChatGPT lures to spread malware on Facebook

Meta said in a report on May 3 that malware posing as ChatGPT was on the rise across its platforms . The company said that since March 2023, its security teams have uncovered 10 malware families using ChatGPT (and similar themes) to deliver malicious software to users’ devices.

“In one case, we’ve seen threat actors create malicious browser extensions available in official web stores that claim to offer ChatGPT-based tools,” said Meta security engineers Duc H. Nguyen and Ryan Victory in  a blog post . “They would then promote these malicious extensions on social media and through sponsored search results to trick people into downloading malware.”

ChatGPT parent company OpenAI closes $300M share sale at $27B-29B valuation

VC firms including Sequoia Capital, Andreessen Horowitz, Thrive and K2 Global are picking up new shares, according to documents seen by TechCrunch. A source tells us Founders Fund is also investing. Altogether the VCs have put in just over $300 million at a valuation of $27 billion to $29 billion . This is separate to a big investment from Microsoft announced earlier this year , a person familiar with the development told TechCrunch, which closed in January. The size of Microsoft’s investment is believed to be around $10 billion, a figure we confirmed with our source.

OpenAI previews new subscription tier, ChatGPT Business

Called ChatGPT Business, OpenAI describes the forthcoming offering as “for professionals who need more control over their data as well as enterprises seeking to manage their end users.”

“ChatGPT Business will follow our API’s data usage policies, which means that end users’ data won’t be used to train our models by default,” OpenAI  wrote in a blog post. “We plan to make ChatGPT Business available in the coming months.”

OpenAI wants to trademark “GPT”

OpenAI applied for a trademark for “GPT,” which stands for “Generative Pre-trained Transformer,” last December. Last month, the company petitioned the USPTO to speed up the process, citing the “myriad infringements and counterfeit apps” beginning to spring into existence.

Unfortunately for OpenAI, its petition was  dismissed  last week. According to the agency, OpenAI’s attorneys neglected to pay an associated fee as well as provide “appropriate documentary evidence supporting the justification of special action.”

That means a decision could take up to five more months.

Auto-GPT is Silicon Valley’s latest quest to automate everything

Auto-GPT is an open-source app created by game developer Toran Bruce Richards that uses OpenAI’s latest text-generating models, GPT-3.5 and GPT-4, to interact with software and services online, allowing it to “autonomously” perform tasks.

Depending on what objective the tool’s provided, Auto-GPT can behave in very… unexpected ways. One Reddit  user  claims that, given a budget of $100 to spend within a server instance, Auto-GPT made a wiki page on cats, exploited a flaw in the instance to gain admin-level access and took over the Python environment in which it was running — and then “killed” itself.

FTC warns that AI technology like ChatGPT could ‘turbocharge’ fraud

FTC chair Lina Khan and fellow commissioners warned House representatives of the potential for modern AI technologies, like ChatGPT, to be used to “turbocharge” fraud in a congressional hearing .

“AI presents a whole set of opportunities, but also presents a whole set of risks,” Khan told the House representatives. “And I think we’ve already seen ways in which it could be used to turbocharge fraud and scams. We’ve been putting market participants on notice that instances in which AI tools are effectively being designed to deceive people can place them on the hook for FTC action,” she stated.

Superchat’s new AI chatbot lets you message historical and fictional characters via ChatGPT

The company behind the popular iPhone customization app  Brass , sticker maker  StickerHub  and  others  is out today with a new AI chat app called  SuperChat , which allows iOS users to chat with virtual characters powered by OpenAI’s ChatGPT . However, what makes the app different from the default experience or the dozens of generic AI chat apps now available are the characters offered which you can use to engage with SuperChat’s AI features.

Italy gives OpenAI to-do list for lifting ChatGPT suspension order

Italy’s data protection watchdog has laid out what OpenAI needs to do for it to lift an order against ChatGPT issued at the  end of last month — when it said it suspected the AI chatbot service was in breach of the EU’s GSPR and ordered the U.S.-based company to stop processing locals’ data.

The DPA has given OpenAI a deadline — of April 30 — to get the regulator’s compliance demands done. (The local radio, TV and internet awareness campaign has a slightly more generous timeline of May 15 to be actioned.)

Researchers discover a way to make ChatGPT consistently toxic

A study co-authored by scientists at the Allen Institute for AI shows that assigning ChatGPT a “persona” — for example, “a bad person,” “a horrible person” or “a nasty person” — through the ChatGPT API increases its toxicity sixfold. Even more concerning, the co-authors found having the conversational AI chatbot pose as certain historical figures, gendered people and members of political parties also increased its toxicity — with journalists, men and Republicans in particular causing the machine learning model to say more offensive things than it normally would.

The research was conducted using the latest version, but not the model currently in preview based on OpenAI’s GPT-4 .

Y Combinator-backed startups are trying to build ‘ChatGPT for X’

YC Demo Day’s Winter 2023 batch features no fewer than four startups that claim to be building “ChatGPT for X.” They’re all chasing after a customer service software market that’ll be worth $58.1 billion by 2023, assuming the rather optimistic prediction from Acumen Research comes true.

Here are the YC-backed startups that caught our eye:

• Yuma , whose customer demographic is primarily Shopify merchants, provides ChatGPT-like AI systems that integrate with help desk software, suggesting drafts of replies to customer tickets.
• Baselit , which uses one of OpenAI’s text-understanding models to allow businesses to embed chatbot-style analytics for their customers.
• Lasso customers send descriptions or videos of the processes they’d like to automate and the company combines ChatGPT-like interface with robotic process automation (RPA) and a Chrome extension to build out those automations.
• BerriAI , whose platform is designed to help developers spin up ChatGPT apps for their organization data through various data connectors.

Italy orders ChatGPT to be blocked

OpenAI has started geoblocking access to its generative AI chatbot, ChatGPT, in Italy .

Italy’s data protection authority has just put out a timely reminder that some countries do have laws that already apply to cutting edge AI: it has  ordered OpenAI to stop processing people’s data locally with immediate effect. The Italian DPA said it’s concerned that the ChatGPT maker is breaching the European Union’s General Data Protection Regulation (GDPR), and is opening an investigation.

1,100+ signatories signed an open letter asking all ‘AI labs to immediately pause for 6 months’

The letter’s signatories include Elon Musk, Steve Wozniak and Tristan Harris of the Center for Humane Technology, among others. The letter calls on “all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4.”

The letter reads:

Contemporary AI systems are now becoming human-competitive at general tasks,[3] and we must ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization? Such decisions must not be delegated to unelected tech leaders. Powerful AI systems should be developed only once we are confident that their effects will be positive and their risks will be manageable.

OpenAI connects ChatGPT to the internet

OpenAI launched plugins for ChatGPT, extending the bot’s functionality by granting it access to third-party knowledge sources and databases, including the web. Available in alpha to ChatGPT users and developers on the waitlist , OpenAI says that it’ll initially prioritize a small number of developers and subscribers to its premium ChatGPT Plus plan before rolling out larger-scale and  API  access.

OpenAI launches GPT-4, available through ChatGPT Plus

GPT-4 is a powerful image- and text-understanding AI model from OpenAI. Released March 14, GPT-4 is available for paying ChatGPT Plus users and through a public API. Developers can sign up on a waitlist to access the API.

ChatGPT is available in Azure OpenAI service

ChatGPT is generally available through the Azure OpenAI Service , Microsoft’s fully managed, corporate-focused offering. Customers, who must already be “Microsoft managed customers and partners,” can apply here for special access .

OpenAI launches an API for ChatGPT

OpenAI makes another move toward monetization by launching a paid API for ChatGPT . Instacart, Snap (Snapchat’s parent company) and Quizlet are among its initial customers.

Microsoft launches the new Bing, with ChatGPT built in

At a press event in Redmond, Washington, Microsoft announced its long-rumored integration of OpenAI’s GPT-4 model into Bing , providing a ChatGPT-like experience within the search engine. The announcement spurred a 10x increase in new downloads for Bing globally, indicating a sizable consumer demand for new AI experiences.

Other companies beyond Microsoft joined in on the AI craze by implementing ChatGPT, including OkCupid , Kaito , Snapchat and Discord — putting the pressure on Big Tech’s AI initiatives, like Google .

OpenAI launches ChatGPT Plus, starting at $20 per month

After ChatGPT took the internet by storm, OpenAI launched a new pilot subscription plan for ChatGPT called ChatGPT Plus , aiming to monetize the technology starting at $20 per month. A month prior, OpenAI posted a waitlist for “ChatGPT Professional” as the company began to think about monetizing the chatbot.

OpenAI teases ChatGPT Professional

OpenAI said that it’s “starting to think about how to monetize ChatGPT” in an announcement on the company’s official Discord server. According to a waitlist link OpenAI posted in Discord, the monetized version will be called ChatGPT Professional . The waitlist document includes the benefits of this new paid version of the chatbot which include no “blackout” windows, no throttling and an unlimited number of messages with ChatGPT — “at least 2x the regular daily limit.”

ShareGPT lets you easily share your ChatGPT conversations

A week after ChatGPT was released into the wild , two developers — Steven Tey and Dom Eccleston — made a Chrome extension called ShareGPT to make it easier to capture and share the AI’s answers with the world.

ChatGPT first launched to the public as OpenAI quietly released GPT-3.5

GPT-3.5 broke cover with ChatGPT , a fine-tuned version of GPT-3.5 that’s essentially a general-purpose chatbot. ChatGPT can engage with a range of topics, including programming, TV scripts and scientific concepts. Writers everywhere rolled their eyes at the new technology, much like artists did with OpenAI’s DALL-E model , but the latest chat-style iteration seemingly broadened its appeal and audience.

What is ChatGPT? How does it work?

ChatGPT is a general-purpose chatbot that uses artificial intelligence to generate text after a user enters a prompt, developed by tech startup OpenAI . The chatbot uses GPT-4, a large language model that uses deep learning to produce human-like text.

When did ChatGPT get released?

November 30, 2022 is when ChatGPT was released for public use.

What is the latest version of ChatGPT?

Both the free version of ChatGPT and the paid ChatGPT Plus are regularly updated with new GPT models. The most recent model is GPT-4 .

Can I use ChatGPT for free?

There is a free version of ChatGPT that only requires a sign-in in addition to the paid version, ChatGPT Plus .

Who uses ChatGPT?

Anyone can use ChatGPT! More and more tech companies and search engines are utilizing the chatbot to automate text or quickly answer user questions/concerns.

What companies use ChatGPT?

Multiple enterprises utilize ChatGPT, although others may limit the use of the AI-powered tool .

Most recently, Microsoft announced at it’s 2023 Build conference that it is integrating it ChatGPT-based Bing experience into Windows 11. A Brooklyn-based 3D display startup Looking Glass utilizes ChatGPT to produce holograms you can communicate with by using ChatGPT.  And nonprofit organization Solana officially integrated the chatbot into its network with a ChatGPT plug-in geared toward end users to help onboard into the web3 space.

What does GPT mean in ChatGPT?

GPT stands for Generative Pre-Trained Transformer.

What’s the difference between ChatGPT and Bard?

Much like OpenAI’s ChatGPT, Bard is a chatbot that will answer questions in natural language. Google announced at its 2023 I/O event that it will soon be adding multimodal content to Bard, meaning that it can deliver answers in more than just text, responses can give you rich visuals as well. Rich visuals mean pictures for now, but later can include maps, charts and other items.

ChatGPT’s generative AI has had a longer lifespan and thus has been “learning” for a longer period of time than Bard.

What is the difference between ChatGPT and a chatbot?

A chatbot can be any software/system that holds dialogue with you/a person but doesn’t necessarily have to be AI-powered. For example, there are chatbots that are rules-based in the sense that they’ll give canned responses to questions.

ChatGPT is AI-powered and utilizes LLM technology to generate text after a prompt.

Can ChatGPT write essays?

Can chatgpt commit libel.

Due to the nature of how these models work , they don’t know or care whether something is true, only that it looks true. That’s a problem when you’re using it to do your homework, sure, but when it accuses you of a crime you didn’t commit, that may well at this point be libel.

We will see how handling troubling statements produced by ChatGPT will play out over the next few months as tech and legal experts attempt to tackle the fastest moving target in the industry.

Does ChatGPT have an app?

Yes, there is now a free ChatGPT app that is currently limited to U.S. iOS users at launch. OpenAi says an android version is “coming soon.”

What is the ChatGPT character limit?

It’s not documented anywhere that ChatGPT has a character limit. However, users have noted that there are some character limitations after around 500 words.

Does ChatGPT have an API?

Yes, it was released March 1, 2023.

What are some sample everyday uses for ChatGPT?

Everyday examples include programing, scripts, email replies, listicles, blog ideas, summarization, etc.

What are some advanced uses for ChatGPT?

Advanced use examples include debugging code, programming languages, scientific concepts, complex problem solving, etc.

How good is ChatGPT at writing code?

It depends on the nature of the program. While ChatGPT can write workable Python code, it can’t necessarily program an entire app’s worth of code. That’s because ChatGPT lacks context awareness — in other words, the generated code isn’t always appropriate for the specific context in which it’s being used.

Can you save a ChatGPT chat?

Yes. OpenAI allows users to save chats in the ChatGPT interface, stored in the sidebar of the screen. There are no built-in sharing features yet.

Are there alternatives to ChatGPT?

Yes. There are multiple AI-powered chatbot competitors such as Together , Google’s Bard and Anthropic’s Claude , and developers are creating open source alternatives . But the latter are harder — if not impossible — to run today.

The Google-owned research lab DeepMind claimed that its next LLM, will rival, or even best, OpenAI’s ChatGPT . DeepMind is using techniques from AlphaGo, DeepMind’s AI system that was the first to defeat a professional human player at the board game Go, to make a ChatGPT-rivaling chatbot called Gemini.

Apple is developing AI tools to challenge OpenAI, Google and others. The tech giant created a chatbot that some engineers are internally referring to as “Apple GPT,” but Apple has yet to determine a strategy for releasing the AI to consumers.

How does ChatGPT handle data privacy?

OpenAI has said that individuals in “certain jurisdictions” (such as the EU) can object to the processing of their personal information by its AI models by filling out  this form . This includes the ability to make requests for deletion of AI-generated references about you. Although OpenAI notes it may not grant every request since it must balance privacy requests against freedom of expression “in accordance with applicable laws”.

The web form for making a deletion of data about you request is entitled “ OpenAI Personal Data Removal Request ”.

In its privacy policy, the ChatGPT maker makes a passing acknowledgement of the objection requirements attached to relying on “legitimate interest” (LI), pointing users towards more information about requesting an opt out — when it writes: “See here  for instructions on how you can opt out of our use of your information to train our models.”

What controversies have surrounded ChatGPT?

Recently, Discord announced that it had integrated OpenAI’s technology into its bot named Clyde where two users tricked Clyde into providing them with instructions for making the illegal drug methamphetamine (meth) and the incendiary mixture napalm.

An Australian mayor has publicly announced he may sue OpenAI for defamation due to ChatGPT’s false claims that he had served time in prison for bribery. This would be the first defamation lawsuit against the text-generating service.

CNET found itself in the midst of controversy after Futurism reported the publication was publishing articles under a mysterious byline completely generated by AI. The private equity company that owns CNET, Red Ventures, was accused of using ChatGPT for SEO farming, even if the information was incorrect.

Several major school systems and colleges, including New York City Public Schools , have banned ChatGPT from their networks and devices. They claim that the AI impedes the learning process by promoting plagiarism and misinformation, a claim that not every educator agrees with .

There have also been cases of ChatGPT accusing individuals of false crimes .

Where can I find examples of ChatGPT prompts?

Several marketplaces host and provide ChatGPT prompts, either for free or for a nominal fee. One is PromptBase . Another is ChatX . More launch every day.

Can ChatGPT be detected?

Poorly. Several tools claim to detect ChatGPT-generated text, but in our tests , they’re inconsistent at best.

Are ChatGPT chats public?

No. But OpenAI recently disclosed a bug, since fixed, that exposed the titles of some users’ conversations to other people on the service.

Who owns the copyright on ChatGPT-created content or media?

The user who requested the input from ChatGPT is the copyright owner.

What lawsuits are there surrounding ChatGPT?

None specifically targeting ChatGPT. But OpenAI is involved in at least one lawsuit that has implications for AI systems trained on publicly available data, which would touch on ChatGPT.

Are there issues regarding plagiarism with ChatGPT?

Yes. Text-generating AI models like ChatGPT have a tendency to regurgitate content from their training data.

• Interesting
• Scholarships
• UGC-CARE Journals

Step-by-Step Guide: How to Use ChatGPT to Write a Literature Review With Prompts

Step-by-Step Guide: How to Use ChatGPT for Writing a Literature Review

Table of contents

A step-by-step guide: how to use chatgpt for writing a literature review, chatgpt prompts to write a literature review.

Writing a literature review can be a challenging task for researchers and students alike. It requires a comprehensive understanding of the existing body of research on a particular topic. However, with the advent of advanced language models like ChatGPT, the process has become more accessible and efficient.

In this step-by-step guide, ilovephd will explore how you can leverage ChatGPT to write a compelling literature review that is both informative.

Step 1: Defining Your Research Objective Before diving into the literature review process, it is crucial to define your research objective.

Clearly articulate the topic, research question, or hypothesis you aim to address through your literature review. This step will help you maintain focus and guide your search for relevant sources.

Step 2: Identifying Keywords and Search Terms To effectively use ChatGPT to assist in your literature review, you need to identify relevant keywords and search terms related to your research topic.

These keywords will help you narrow down your search and gather pertinent information. Consider using tools like Google Keyword Planner or other keyword research tools to discover commonly used terms in your field.

Step 3: Familiarizing Yourself with ChatGPT Before engaging with ChatGPT, it is essential to understand its capabilities and limitations. Familiarize yourself with the prompts and commands that work best with the model.

Keep in mind that ChatGPT is an AI language model trained on a vast amount of data, so it can provide valuable insights and suggestions, but it’s important to critically evaluate and validate the information it generates.

Step 4: Generating an Initial Literature Review Outline Start by creating an outline for your literature review. Outline the main sections, such as the introduction, methodology, results, discussion, and conclusion.

Within each section, jot down the key points or subtopics you want to cover. This will help you organize your thoughts and structure your review effectively.

Step 5: Engaging with ChatGPT for Research Assistance Once you have your outline ready, engage with ChatGPT for research assistance.

Begin by providing a clear and concise prompt that specifies the topic, context, and any specific questions you have. For example, “What are the current trends in [your research topic]?” or “Can you provide an overview of the main theories on [your research question]?”

Step 6: Reviewing and Selecting Generated Content ChatGPT will generate a response based on your prompt. Carefully review the content generated, considering its relevance, accuracy, and coherence.

Extract key points, relevant references, and insightful arguments from the response and incorporate them into your literature review. Be sure to cite and attribute the sources appropriately.

Step 7: Ensuring Coherence and Flow While ChatGPT can provide valuable content, it’s important to ensure the coherence and flow of your literature review.

Use your critical thinking skills to connect the generated content with your research objective and existing knowledge. Rearrange, rephrase, and expand upon the generated text to ensure it aligns with the structure and purpose of your review.

Step 8: Editing and Proofreading Once you have incorporated the generated content into your literature review, thoroughly edit and proofread the document.

Check for grammatical errors, consistency in referencing, and overall clarity. This step is crucial to ensure your literature review is polished and professional.

Prompts you can use when engaging with ChatGPT for research assistance in writing a literature review:

• “Can you provide an overview of the main theories and concepts related to [your research topic]?”
• “What are the current trends and developments in [your research field]?”
• “Can you suggest some key studies or research papers on [specific aspect of your research topic]?”
• “What are the main methodologies used in conducting research on [your research topic]?”
• “Can you provide a critical analysis of the existing literature on [your research question]?”
• “Are there any gaps or areas of controversy in the literature on [your research topic] that need further exploration?”
• “What are the key findings and conclusions from the most recent studies on [your research topic]?”
• “Can you suggest some reputable journals or publications explore for relevant literature in [your research field]?”
• “What are the different perspectives or schools of thought in the literature on [your research topic]?”
• “Can you provide a summary of the historical background and evolution of research on [your research topic]?”

Remember to provide clear and specific instructions in your prompts to guide ChatGPT in generating relevant and accurate content for your literature review.

Using ChatGPT to write a literature review can greatly facilitate the research process. By following a step-by-step approach, researchers can effectively leverage ChatGPT’s capabilities to gather insights, generate content, and enhance the quality of their literature review. However, it is important to approach the generated content critically, validate it with reliable sources, and ensure coherence within the review.

• Academic Writing
• AI writing tool
• literature review guide
• literature review tips
• research assistance
• research process
• research writing
• write literature review

Top 10 iLovePhD Articles of 2023

Ramalingaswami re-entry fellowship – re-ignite your research career in india, what is agi in research, email subscription.

iLovePhD is a research education website to know updated research-related information. It helps researchers to find top journals for publishing research articles and get an easy manual for research tools. The main aim of this website is to help Ph.D. scholars who are working in various domains to get more valuable ideas to carry out their research. Learn the current groundbreaking research activities around the world, love the process of getting a Ph.D.

WhatsApp Channel

Join iLovePhD WhatsApp Channel Now!

Contact us: [email protected]

Copyright © 2019-2024 - iLovePhD

• Artificial intelligence

How To Use ChatGPT To Write A Literature Review: Prompts & References

In the rapidly evolving world of academic research, the integration of AI tools like ChatGPT has transformed the traditional approach to literature reviews. As a researcher, you should also leverage on this tool to make your research work easier.

In this post, explore how ChatGPT can enhance the literature review process. We’ll explore how specific prompts can effectively guide this advanced AI model to generate insightful content, while ensuring accuracy, relevance, and academic integrity in their scholarly work.

How to Use ChatGPT for Writing a Literature Review

Understanding chatgpt’s limitations.

While it can efficiently generate content, streamline the research process, and provide a comprehensive understanding of relevant literature, its capabilities are not without constraints. Here are some for you to consider:

Dependence On Pre-Existing Datasets

Since ChatGPT is a language model trained on available data, it may not include the most recent research papers or cutting-edge findings in a specific field. This gap can lead to a lack of current state-of-research insights, particularly crucial in fields like technology and science where advancements happen rapidly.

May Lack Depth And Context

ChatGPT, while able to produce summaries and synthesize information, might not fully grasp the nuanced arguments or complex theories specific to a research topic. This limitation necessitates that researchers critically evaluate and supplement AI-generated text with thorough analysis and insights from recent systematic reviews and primary sources.

Risk Of Plagiarism

Although ChatGPT can generate human-like text, it’s vital to ensure that the content for your literature review is original and properly cited. Relying solely on ChatGPT to write a literature review defeats the purpose of engaging deeply with the material and developing a personal understanding of the literature.

Not A Total Replacement of A Researcher

While ChatGPT can assist non-native English speakers in crafting clear and concise academic writing, it’s not a replacement for the human ability to contextualize and interpret research findings. Researchers must guide the AI model with specific prompts and leverage it as a tool rather than a substitute for comprehensive analysis.

By keeping these limitations in mind, ChatGPT can be a valuable aid in the literature review process, but it should be used judiciously and in conjunction with traditional research methods.

Defining Research Objective

When starting on writing a literature review, the initial step involves using ChatGPT to define your research question or hypothesis.

The AI model’s ability to respond with a summary of the current state of research in your field can provide a comprehensive understanding, especially for systematic reviews or research papers.

For example, by inputting a prompt related to your research topic, ChatGPT can generate human-like text, summarizing prior research and highlighting relevant literature.

One insider tip for effectively using ChatGPT in the literature review process is to leverage its natural language processing capabilities to identify relevant keywords.

These keywords are crucial for non-native English speakers or those new to a research field, as they streamline the search for pertinent academic writing. Additionally, ChatGPT can guide you in understanding the context of your research topic, offering insights that are often challenging to find.

Using AI language models like ChatGPT for generating content for your literature review is efficient and effective, saving valuable time. However, it’s vital to critically evaluate the generated text to ensure it aligns with your research objectives and to avoid plagiarism.

ChatGPT’s ability to synthesize large amounts of information can aid in developing a clear and concise outline, but remember, it’s a guide, not a replacement for human analysis.

Despite these limitations, ChatGPT provides a unique advantage in conducting literature reviews. It can automate mundane tasks, allowing researchers to focus on analysis and critical thinking.

Identifying Keywords and Search Terms

Using ChatGPT to identify relevant keywords related to your research topic can significantly streamline your workflow.

For instance, when you input a summary of your research question into ChatGPT, the AI model can generate a list of pertinent keywords.

These keywords are not just randomly selected; they are based on the vast amounts of information in ChatGPT’s dataset, making them highly relevant and often inclusive of terms that are current in your research field.

An insider tip for leveraging ChatGPT effectively is to guide the AI with clear and concise prompts.

For example, asking ChatGPT to: “summarize key themes in [specific field] research papers from the last five years” can yield a list of keywords and phrases that are not only relevant but also reflective of the current state of research.

This approach is particularly beneficial for conducting systematic reviews or for non-native English speakers who might be unfamiliar with specific academic jargon.

While ChatGPT can provide a comprehensive understanding of relevant literature and help automate the identification of keywords, it’s important to critically evaluate the generated content.

Researchers should use ChatGPT as a tool to augment their research process, not as a replacement for human insight.

It’s crucial to mind the limitations of the AI model and ensure that the keywords identified align with the research topic and objectives.

Creating an Initial Literature Review Outline

The key to using ChatGPT effectively in crafting an initial outline lies in its ability to generate content based on specific prompts.

For instance, a researcher working on organic photovoltaic devices can input a prompt into ChatGPT, such as “Help me create a structure for a literature review on organic photovoltaic devices.”

The AI model, using its comprehensive understanding of the research topic, can then produce a preliminary structure, including sections like:

• Introduction
• Advances in materials and technology, performance, and efficiency.

This generated outline serves as a valuable starting point. It helps in organizing thoughts and determining the key areas that the literature review should cover. I

mportantly, researchers can refine and expand this initial outline as they delve deeper into their topic, ensuring it aligns with their specific research question and the current state of research.

However, while ChatGPT can streamline the review process and save valuable time in creating an initial outline, researchers should not solely rely on it.

The content generated by ChatGPT must be critically evaluated and supplemented with in-depth research. This involves:

• Reading systematic reviews
• Reading research papers, and
• Summarizing relevant literature to ensure the review is comprehensive and up-to-date.

Get ChatGPT To Help You During Research, Using The Right Prompts

The key to effectively using ChatGPT in this process lies in crafting the right prompts, guiding the AI to generate relevant and useful content. 

When initiating a literature review, the prompt should aim for a broad understanding of the research topic. For instance, asking ChatGPT to:

• “Give a brief overview of research done on [topic]”
• “What are some of the recent findings on the [topic] in research?” or 
• “Summarize the historical development of [topic] in academia”

Helps in capturing the general landscape of the field. These prompts assist in identifying key theories, methodologies, and authors within the research area. As the review progresses, more specific prompts are necessary to delve deeper into individual studies. Queries like:

• “Summarize the main arguments and findings of [specific paper]” or
• “What are the strengths and weaknesses of [specific paper]?”

enable ChatGPT to provide detailed insights into particular research papers, aiding in understanding their contribution to the broader field. Comparative prompts are also crucial in synthesizing information across multiple works. Asking ChatGPT to:

• “Compare and contrast the methodologies of [paper 1] and [paper 2]” or
• “How do the findings of [paper 1] and [paper 2] agree or disagree?”

helps in discerning the nuances and disparities in the literature. In the final stages of the literature review, prompts should focus on summarizing findings and identifying emerging trends or gaps. For example:

• “What trends or patterns have emerged from the literature on [topic]?” or
• “What future research directions are suggested by the literature on [topic]?”

We will share more on these ChatGPT prompts in the later part of this post, read on.

Reviewing ChatGPT’s Responses

When using ChatGPT to write a literature review, it’s crucial to critically evaluate its responses.

Firstly, researchers should cross-reference the information provided by ChatGPT with actual research papers.

This step ensures the accuracy of the data and helps in identifying any discrepancies or outdated information, given that ChatGPT’s dataset may not include the most recent studies.

Another essential aspect is assessing the coherence and depth of the AI-generated text. ChatGPT can summarize and synthesize information efficiently, but it might not capture the nuances of complex theories or research arguments.

Researchers should ensure that the content aligns with their research question and systematically reviews the topic comprehensively. This is where a researcher’s value comes in.

Additionally, verifying the originality of the content is vital to avoid plagiarism. While ChatGPT can generate human-like text, researchers must ensure that the AI-generated content is used as a guide rather than a verbatim source. 

Proper citations and references are essential to maintain the integrity of the literature review. Avoid torpedoing your own research by committing plagiarism.

Ensuring Coherence and Flow

One of the challenges when using such advanced AI language models is ensuring the coherence and flow of the final document. This aspect is crucial as it determines the readability and academic rigor of the literature review.

ChatGPT can generate vast amounts of content on a wide range of topics, responding efficiently to prompts and synthesizing information from its extensive dataset.

However, the content generated by ChatGPT, while informative, might not always align seamlessly with the specific research question or maintain a consistent narrative flow.

To tackle this, researchers need to take an active role in guiding ChatGPT and subsequently refining its output.

A practical approach is to use ChatGPT as a starting point, leveraging its ability to quickly provide summaries, synthesize relevant literature, and identify key references and keywords related to the research topic. For example, prompts like:

• “Summarize the current research on [topic]” or
• “Identify key debates in [topic]”

Can yield valuable initial insights.

Once this foundational information is obtained, the crucial task is to carefully review and edit the AI-generated content.

This involves connecting the dots between different sections, ensuring that each part contributes meaningfully to addressing the research question, and refining the language to maintain academic standards.

It’s also essential to check for and avoid plagiarism, ensuring that all sources are correctly cited.

In addition, considering the vast amounts of information ChatGPT can access, it’s vital to verify the accuracy and relevance of the content.

Researchers should cross-reference AI-generated summaries with actual research papers, especially the most recent ones, as ChatGPT’s dataset may not include the latest studies.

Editing and Proofreading

Now that your literature review is mostly written out, now focus on the editing and proofreading. The content generated by ChatGPT needs to be meticulously reviewed and edited. Here are the steps:

• Verifying the accuracy of the information. Researchers must cross-check the AI-generated content against actual research papers and systematic reviews. This ensures that the latest studies are accurately represented.
• Improve coherence and flow. Researchers should restructure sentences, ensure logical progression of ideas, and maintain a consistent academic tone throughout the document.
• Checking for plagiarism. Despite ChatGPT’s ability to generate human-like text, researchers must ensure that all sources are correctly cited and that the review does not inadvertently replicate existing material.
• Check Grammar and Spelling: Editing should encompass grammar checks, vocabulary refinement, and ensuring that the language used is appropriate for an academic audience.
• Update Citation: Review citation, or reference list to ensure everything is cited correctly, and the citation list is written out to your required standard, be it MLA, Chicago, or APA.

What ChatGPT Prompts To Use When Writing A Literature Review?

There are many ways to use ChatGPT to write literature review, usually by using the right prompts. Here’s how specific types of prompts can be effectively employed, with multiple examples for each category:

• “Provide a comprehensive overview of the latest research on [topic].”
• “Summarize the current understanding and key findings in the field of [topic].”
• “Detail the dominant theoretical frameworks currently used in [topic].”
• “Describe the evolution of theoretical approaches in [topic] over the past decade.”
• “Identify and discuss the major debates or controversies in [topic].”
• “What are the conflicting viewpoints or schools of thought in [topic]?”
• “List the leading researchers in [topic] and summarize their key contributions.”
• “Who are the emerging authors in [topic], and what unique perspectives do they offer?”
• “Explain the most common research methodologies used in studies about [topic].”
• “How have the methodologies in [topic] research evolved recently?”
• “Trace the historical development and major milestones in [topic].”
• “Provide a timeline of the key discoveries and shifts in understanding in [topic].”
• “What significant paradigm shifts have occurred in [topic] in the last twenty years?”
• “How has the focus of research in [topic] changed over time?”
• “Analyze the methodology and conclusions of [specific paper].”
• “Discuss the impact and reception of [specific paper] in the field of [topic].”
• “Compare the results and methodologies of [paper 1] and [paper 2] in [topic].”
• “How do [paper 1] and [paper 2] differ in their approach to [topic]?”
• “Based on current literature, what are the suggested future research directions in [topic]?”
• “Identify gaps in the literature of [topic] that could be explored in future studies.”

By using these types of prompts, researchers can guide ChatGPT to produce content that is not only relevant to their literature review but also rich in detail and scope.

Wrapping Up: Use Other AI Tools Too, Not Just ChatGPT

In conclusion, while ChatGPT serves as a powerful ally in the literature review process, it’s important to recognize it as one of many AI tools available to researchers as well. Diversifying your AI toolkit can enhance the depth and breadth of your review, offering varied perspectives and methodologies.

As AI continues to evolve, embracing a range of these tools can lead to more comprehensive, nuanced, and innovative academic writing, expanding the horizons of research and scholarly exploration beyond what we currently envision.

Dr Andrew Stapleton has a Masters and PhD in Chemistry from the UK and Australia. He has many years of research experience and has worked as a Postdoctoral Fellow and Associate at a number of Universities. Although having secured funding for his own research, he left academia to help others with his YouTube channel all about the inner workings of academia and how to make it work for you.

Thank you for visiting Academia Insider.

We are here to help you navigate Academia as painlessly as possible. We are supported by our readers and by visiting you are helping us earn a small amount through ads and affiliate revenue - Thank you!

2024 © Academia Insider

Can I Use ChatGPT to Write Online Reviews?

Your business needs online reviews. Over 99.9% of customers read reviews when shopping online. For over half of consumers, more reviews = a better company reputation. And if your overall rating drops below 3.3 stars, customers are likely to choose somewhere else to shop.

However, collecting these reviews is sometimes easier said than done. To get five-star reviews across the web, you need to identify happy customers, find the right time and place to ask them to write a review, and spend time managing and responding to these reviews on a variety of platforms. 

This is why some businesses might be tempted to use ChatGPT, a newly popular artificial intelligence chatbot, to write online reviews. ChatGPT is capable of writing reviews of a product or business. But just because you can do something doesn’t mean you should. Read our breakdown of how ChatGPT works and whether or not you should use it to write reviews online. 

What is ChatGPT?

These days, ChatGPT is the latest internet buzzword that’s on the tip of everyone’s tongue. ChatGPT is an artificial intelligence chatbot created by OpenAI and originally launched in November 2022. 

This chatbot interacts with you in a conversational, humanlike way, and can follow instructions to write anything from poetry to computer programs to essays. You can access the bot for free with an OpenAI account. A paid subscription version is now available, too.

Can ChatGPT write online reviews?

Yes. ChatGPT is able to write reviews of a product or business. In fact, YouTube is already swamped with videos teaching you how to write Amazon reviews or other product reviews using ChatGPT. 

These tutorials walk you through how to create a review with ChatGPT, showing how this tool can produce a review that talks about the pros and cons of a product and how it can be used. While it may be okay for buyers or consumers to ask ChatGPT to help them write an article about a product, it’s a different story for businesses. As a business owner or representative, you should not use ChatGPT to write reviews about your own product.

ChatGPT can be a helpful resource to create content for your company website, such as blog posts that share more information about your product, its features, and how it can solve your customers’ problems. But it is not ethical to generate fake online reviews with ChatGPT. 

Pros and cons of writing reviews with ChatGPT

Like any digital tool, ChatGPT has both pros and cons. It’s easy, fast, and convenient to ask the bot a question and get an immediate, detailed response.  

One journalist, who asked ChatGPT to write a review of the iPhone 14 Pro, said the review flowed well and did a good job of mentioning the product’s user experience. However, the review included inaccurate information, was too favorable, and did not have any personality. 

Interestingly, ChatGPT seems to be programmed to only write positive reviews. A college professor who has taught a class on ChatGPT asked the bot to write a negative review of a business and received a response stating, “It would be unethical for me to produce a negative review of a business.”

However, the bot’s responses tend to sound formal rather than conversational. And you’re taking a risk on the chatbot pulling inaccurate information into its review. OpenAI itself warns users that ChatGPT might generate information that’s harmful, biased, or incorrect.

What’s more, ChatGPT does not and cannot provide any original insight into products or businesses like a human consumer would. Keep in mind, too, that ChatGPT is still in development. While impressive, the bot is continually being refined. 

Why you shouldn’t write fake reviews

The Federal Trade Commission sets standards for endorsements and testimonials used in advertising (in other words, online reviews). These guidelines state that you should not ask for reviews from people who haven’t actually used or experienced your product or service. This means writing fake reviews is actually illegal , as Section 5(a) of the Federal Trade Commission Act states that deceptive practices affecting commerce are prohibited. The FTC has been known to crack down on businesses that manipulate reviews, sometimes requiring these companies to pay millions of dollars as a consequence. 

Your customers need to trust you, and reviews are a way of building trust. But those reviews need to be from genuine customers who have actually interacted with your brand — not from a bot that you instructed yourself. 

OpenAI recently released an AI Text Classifier tool that can help detect whether a piece of writing was produced by ChatGPT or other AI sources. This resource isn’t 100% accurate but is still something to keep in mind — if you use a bot like ChatGPT to write an online review, people may be able to use a tool like this one to detect whether a human actually wrote your content.

At the end of the day, even if it were legal, using ChatGPT to write online reviews just isn’t worth the risk.

Get online reviews the right way

Online reviews are important. They help keep your business not only surviving, but thriving. Of all the ways — ChatGPT isn’t the way to get them. 

Ditch the bot and ask your real customers for reviews instead. You’ll stay legal and above board, and your customers will know they can trust your brand — which will make them return again and again.

© 2024 GGL Projects, Inc.

How to Upload a File to ChatGPT, and Why You Might Want To

You can easily upload a photo or document to ChatGPT, but what for?

You can ask ChatGPT to analyze your files.

ChatGPT  can do many things: It can provide you with a summary of complex topics, brainstorm film ideas with you and even write code for you in different programming languages. But one thing the AI chatbot, developed by  OpenAI , couldn't do for a long time was access and read photos, documents and other files.

The AI chatbot roster -- as with other generative AI tools -- is expansive and growing, with Google Gemini, Microsoft Copilot,  Claude.ai , Perplexity, Dall-E, Midjourney and others on the list. They're collectively poised to transform how you work, how you get information and how companies do business. But it all started with ChatGPT.

If you wanted ChatGPT to analyze information from something like a PDF or an Excel spreadsheet, you were once out of luck. You'd have to type the information from the document into the chat thread without uploading anything.

But that's no longer the case. With ChatGPT-4, the latest version of ChatGPT, you can now upload any file from your device. Read on to understand who can upload files, why you'd want to and how to upload files. Here's everything you need to know.

Who exactly can upload files to ChatGPT?

Right now, to upload a file to ChatGPT, you need to pay for ChatGPT Plus . A subscription to ChatGPT Plus runs $20 a month, and this grants you access to ChatGPT-4 and access to the latest features, including uploading files. 

If you want to upgrade to ChatGPT Plus, open the ChatGPT app on your phone, access the side panel on the left side, tap the three-dot menu at the bottom of the page, go into Subscription and make a payment. You can also subscribe to ChatGPT Plus on your tablet or computer.

Why would you even want to upload files to ChatGPT anyway?

ChatGPT-4 can analyze any file you upload, whether it's a PowerPoint presentation, an Excel spreadsheet, a research paper or a photo. 

If you upload a spreadsheet with financial data, for example, you can ask ChatGPT to create a visual graph of the numbers. If you upload a PowerPoint presentation you did for school, you can ask ChatGPT to give you feedback on the content, and even proofread and correct any mistakes. With a complicated research paper, you can ask ChatGPT to give you a simple summary to read through, along with a bullet list for headlines and key points.

And with a photo, you can ask ChatGPT to explain what's in the image, or give you instructions on how to build something you've photographed. The options as to what you can ask ChatGPT for are limitless. It's up to you to figure out exactly what you want ChatGPT to do with your files.

Before you upload a file to ChatGPT...

Think about your privacy. Any file you upload to ChatGPT is retained indefinitely within the service, and those files may also be used by OpenAI to train its models, so it's best to refrain from uploading files with any important personal information, like your Social Security number, address,  finance documents or phone numbers.

And someone else could potentially gain access to your personal information , so only upload files with information you wouldn't mind other people getting access to.

It's not just privacy. Consider accuracy too. ChatGPT  can give wrong answers , and its dataset does not have  up-to-date information , so you'll want to double-check that the chatbot is accurately proofreading, summarizing or explaining as you'd expect. 

How to upload files to ChatGPT

Now for the easy part: Uploading files to ChatGPT. As long as you're paying for the premium subscription, launch ChatGPT, create a new chat and hit the plus sign to the left of the text field to view your uploading options. Starting from the far left, you can:

• Give ChatGPT access to your camera and take a photo from within the app
• Upload a photo from your camera roll
• Upload a file from the Files app

Once you upload a file (or files), enter your prompt underneath and hit send. ChatGPT will the analyze your file and answer your question.

You can only upload files with a limit of 512MB per file and photos with a limit of 20MB per image. Note : The files in the middle screenshot above have been blurred for privacy reasons.

In the examples below, (left) I uploaded a call sheet for a short film I worked on and asked ChatGPT to provide a list of everyone on set that day and (right) I uploaded four images of a pub that someone had built in their home and asked ChatGPT how I could do the same.

You can ask ChatGPT to summarize, analyze, extract and more.

You can continue asking questions, in regard to the file you uploaded, within the ChatGPT thread.

Editors' note: CNET is using an AI engine to help create some stories. For more, see  this post .

Mobile Guides

• Best iPhone
• Best Galaxy S24 Deals
• Best iPhone Deals
• Samsung Galaxy S24 Review
• Best Android Phones
• Best Samsung Galaxy Phone
• Pixel 8 Pro Review
• iPhone 15 Pro/Pro Max Review
• Best iPhone 15 Deals
• Best Foldable Phones
• Galaxy Z Fold 5 Review
• OnePlus Open Review
• Best Galaxy Z Flip Deals
• Best Wireless Earbuds
• Best Noise Canceling Headphones
• Best Headphones
• Best Over Ear Headphones
• Best Wireless Earbuds and Headphones for Making Calls
• Best Headphones for Work at Home
• Best Noise Canceling Wireless Earbuds
• Best Sounding Wireless Earbuds
• Best Cheap Wireless Earbuds
• Best Wireless Headphones
• Best iPhone 15 Cases
• Best iPhone 14 Cases
• Best Power Bank for iPhone
• Best Airpods Pro Accessories
• Best Magsafe iPhone Accessories
• Best Speakerphone
• Best Wireless Car Charger and Mount
• Best iPhone Fast Charger
• Best Portable Chargers and Power Banks for Android
• Apple Watch Series 8 vs Series 7
• Best Apple Watch Bands
• Best Android Smartwatch
• Apple Watch Ultra Review
• Best Smartwatch
• Best Prepaid Phone Plans
• Best Cheap Phone Plans
• Best Unlimited Data Plans
• Best Phone Plans
• Best Phone Plan Deals
• Best Senior Phone Plans
• Best Family Phone Plans
• Best Travel Phone Plans
• Best Verizon Plans
• Samsung Promo Codes
• Consumer Cellular Coupons
• Verizon Promo Codes
• AT&T Wireless Promo Codes
• Best Buy Coupons
• Motorola Coupon Codes
• OnePlus Promo Codes
• Sony Coupon Codes
• Apple Store Promo Codes

7 Surefire Signs That ChatGPT Has Written an Essay Revealed

Researchers at the University of Cambridge have revealed the seven telltale signs that a piece of written content was generated by ChatGPT , after carefully analyzing more than 150 essays written by high school students and undergraduates.

They found that ChatGPT loves an Oxford Comma, repeats phrases and spits out tautological statements practically empty of meaning at a much higher frequency than humans.

While the findings are interesting, the sample size is quite small. There's also no guarantee that the linguistic habits and techniques identified couldn’t and wouldn't be used by a human. What’s more, AI content detection tools are largely unreliable; there’s still no way to know for certain that any given written content is AI-generated.

Get the latest tech news, straight to your inbox

Stay informed on the top business tech stories with Tech.co's weekly highlights reel.

By signing up to receive our newsletter, you agree to our Privacy Policy . You can unsubscribe at any time.

The 7 Telltale Signs Content is AI-Generated

The researchers at Cambridge analyzed 164 essays written by high school students with four essays written with a helping hand from ChatGPT.

The ChatGPT-assisted essays were generally more information-heavy and had more reflective elements, but the markers at Cambridge found that they lacked the level of comparison and analysis typically found in human-generated content. 

According to UK-based publication The Telegraph , which broke the story, the researchers identified seven key indicators of AI content:

• Frequent use of Latin root words and “vocabulary above the expected level”
• Paragraphs starting with singular words like “however”, and then a comma 
• Lots of numbered lists with colons
• Unnecessary clarificatory language (e.g. “true fact”)
• Tautological language (“Lets come together to unite”)
• Repetition of the same word or phrase twice 
• Consistent and frequent use of Oxford commas in sentences

Are There Any Other Ways to Spot ChatGPT Plagiarism?

Yes and no. There are many tools online that claim to be able to detect AI content, but when I tested a wide range of them last year, I found many to be wildly inaccurate.

For instance, OpenAI’s own text classifier – which was eventually shut down because it performed so poorly – was unable to identify that text written by ChatGPT (effectively itself) was AI-generated.

Even Turnitin has been using automated processes to detect plagiarized content in academic work for years, and they’ve also developed a powerful AI content checker. The company has always maintained that verdicts arrived at by their tools should be treated as an indication, not a cast-iron accusation.

“Given that our false positive rate is not zero” Turnitin explains in a blog post discussing its AI content detection capabilities.

“You as the instructor will need to apply your professional judgment, knowledge of your students, and the specific context surrounding the assignment”.

None of these tools are infallible – and worse still, many of the free ones you’ll find lurking at the top of the Google Search results are completely and utterly useless.

Is It Wrong to Use AI for School or College Work?

While asking AI tools like ChatGPT and Gemini to write you an essay isn’t quite “plagiarism” in the same way copying content written by other people and passing it off as your own is, it’s certainly not advised.

Whether it’s objectively plagiarism or not is likely irrelevant – the educational institution you’re enrolled in has probably created guidelines explicitly banning generative AI. Many universities have already taken a similar approach to peer review and other academic processes.

Besides, the whole point of writing an essay is to consider the range of ideas and views on the topic you’re writing about and evaluate them using your head. Getting an AI to do it for you defeats the whole point of writing the essay in the first place.

Our advice – considering the consequences of being accused of plagiarism while at university – is to stick to the rules. Who knows – you might learn something while you're at it!

We're sorry this article didn't help you today – we welcome feedback, so if there's any way you feel we could improve our content, please email us at [email protected]

• Artificial Intelligence

Written by:

Study: 77% of Businesses Have Faced AI Security Breaches

AI systems are particularly vulnerable to security...

All the New Copilot Features Microsoft Revealed for Windows 11

Email drafts, meeting recaps, and much more: The average...

GPT-5: OpenAI May Launch “Better” Model for ChatGPT This Summer

Sam Altman says GPT-4 "kinda sucks" but says he's excited...

What Is AI Washing, and Why Are Companies Being Fined For It?

Two firms have just been fined for making false and...

More From Forbes

The tell-tale signs students are using chatgpt to help write their essays.

• Share to Facebook
• Share to Twitter
• Share to Linkedin

Researchers have identified key features of ChatGPT-generated content that makes it easier to spot ... [+] (Pic: Getty Creative)

Researchers have identified tell-tale signs that students have used AI to help write their essays.

Excessive used of words derived from Latin, using unnecessary words and repeated use of the Oxford comma are among the hallmarks of using a generative chatbot to complete coursework, researchers found .

But while students taking part in the trial said they found using AI had some advantages, they acknowledged that relying on it completely would likely result in work of a low standard.

The impact of generative AI on education has been exercising educators since Open AI launched ChatGPT — a chatbot that generates text by predicting which words are likely to follow a particular prompt — in November 2022.

While some regard AI as a potentially transformative technology, creating a more inclusive and personalized education, for others it makes it impossible to trust coursework grades. Even academics have not been immune to using AI to enhance their work.

Now researchers at Cambridge University have tried to see if they could identify characteristics of AI’s writing style that could make it easy to spot.

And although their trial was small scale, they say it has the potential to help teachers work out which students used AI in their essays, and which did not.

Three undergraduates were enlisted to write two essays each with the help of ChatGPT, which were then compared with essays on the same topic written by 164 high school students. The undergraduates were then interviewed about their experience of using AI.

Russia s Ivan Khurs Spy Ship Keeps Tabs On Ukrainian Radars And Missiles No Wonder The Ukrainians Have Been Hunting The Ship For A Year

Ex trump attorney john eastman should be disbarred over 2020 election interference charges judge says, baltimore bridge collapse blamed on dei as the attack on dei continues.

(Undergraduates were included in the study because ChatGPT requires users to be 18 or over).

The ChatGPT essays performed better on average, being marked particularly highly for ‘information’ and ‘reflection’. They did poorly, however, for ‘analysis’ and ‘comparison’ — differences the researchers suggest reflect the chatbot’s strengths and weaknesses.

But when it comes to style, there were a number of features that made the ChatGPT assisted version easily recognizable.

The default AI style “echoes the bland, clipped, and objective style that characterizes much generic journalistic writing found on the internet,” according to the researchers, who identified a number of key features of ChatGPT content:

• A high frequency of words with a Latin root, particularly multisyllable words and a vocabulary above the expected level;
• Paragraphs starting with specific markers, such as ‘however’, ‘moreover’ and ‘overall’, followed by a comma;
• Numbered lists, with items followed by colons;
• Pleonasms: using unnecessary words, such as ‘free gift’ or ‘true fact’;
• Tautology: saying the same thing twice, such as ‘We must come together to unite’;
• Repeating words or phrases;
• Consistent use of Oxford commas, a comma used after the penultimate item in a list, before ‘and’ or ‘or’, for example “ChatGPT has many uses for teaching, learning at home, revision, and assessment”.

Although the students taking part in the trial used ChatGPT to different extents, from copying and pasting whole passages to using it as prompts for further research, there was broad agreement that it was useful for gathering information quickly, and that it could be integrated into essay writing through specific prompts, on topics and essay structure, for example.

But the students also agreed that using AI to write the essay would produce work of a low academic standard.

“Despite the small sample size, we are excited about these findings as they have the capacity to inform the work of teachers as well as students,” said Jude Brady of Cambridge University Press and Assessment, lead researcher on the study.

Future work should include larger and more representative sample sizes of students, she said. Learning to use and detect generative AI was an increasingly important part of digital literacy, she added.

“We hope our research might help people to identify when a piece of text has been written by ChatGPT,” she said.

• Editorial Standards
• Reprints & Permissions

Altmetric Score

Review of: can chatgpt code the technical part of a bachelor's thesis in informatics.

Rahimah Kassim 1

Affiliation

• Universiti Kuala Lumpur, Malaysia

The article provides an interesting exploration of the potential of Large Language Models, particularly focusing on ChatGPT, with computer code writing for Bachelor's theses in the field of Information Systems at Dalarna University, Sweden.  The study is well-structured, and the critical dialog approach used in assessing ChatGPT capabilities provides an important dimension to the evaluation. 

Here are some comments:

-Introduction: The introduction acknowledges the novelty of ChatGPT and its implications; however, a broader review of existing literature on the use of AI in education and coding will provide a more comprehensive background, including previous studies on LLMs in similar contexts. -Methodology: The methodology section is detailed and well-organized. However, it might benefit from a brief explanation of why the critical dialog approach was chosen over other potential methods.

-Results: Tables 1, 2, and 3 are informative, but it might be helpful to include a brief summary or interpretation of the key findings directly in the text. 

-Consider including visual aids, such as graphs or charts, to enhance the presentation of results and make the article more engaging.

-Overall, the study presents a valuable contribution to understanding the role of LLMs in academic coding tasks, and addressing these suggestions can further strengthen its impact. The findings contribute to the nascent body of research on the application of LLMs in education. These comments are intended to enhance the clarity and effectiveness of the article. 

No comments yet.

• Side Hustles
• Power Players
• Young Success
• Save and Invest
• Become Debt-Free
• Land the Job
• Closing the Gap
• Science of Success
• Pop Culture and Media
• Psychology and Relationships
• Health and Wellness
• Real Estate
• Most Popular

Related Stories

• Get Ahead 5 high-paying tech skills   companies are hiring for now
• Work 4 things to prioritize when applying for   jobs, says hiring pro: ‘Be selective’
• Work How to find your dream job amid layoffs:   Interview prep, resume tips, and more
• Land the Job Former Google recruiter’s No. 1 job   interview tip: Teach him something
• Land the Job How to use ChatGPT to prep for a job   interview, says ex-Disney recruiter

The No. 1 AI mistake job seekers make, from a career expert: So many people use ChatGPT 'in exactly the wrong way'

As a leader at the education nonprofit Khan Academy, I was thrilled when ChatGPT came out in November 2022. It meant we could use generative AI to provide personalized tutoring to more kids than ever.

But as a hiring manager and cofounder of a career development business who's trained first-gen students at CUNY and MBAs at Harvard Business School alike, I was heartbroken to see that so many job seekers were using these tools in exactly the wrong way. 

They forgot that no matter how exciting this new technology is, humans are still in charge of the hiring process. Which is why having a robot write your resume is a recipe for disaster.

But given that I wrote the literal book on using ChatGPT in your job search , I know you can still turn to AI to make your resume shine. Used properly, it can help you land the interview — and ultimately the job. 

The wrong way to use AI for your resume

In my experience, most job seekers using ChatGPT or other AI platforms begin with a prompt like "Generate a marketing resume." This might seem like a great place to start, but it's the biggest mistake you could make. Here's why: 

The results are massively generic 

Take this summary, for instance:

As a hiring manager, the first thing I'm always looking for is evidence of specific accomplishments. When I scan this, though, my first thought is "Wow — this candidate is great at buzzwords, but not so great at actual marketing." 

That's hardly the first impression you want to make when employers spend seven seconds , on average, reviewing your resume!

ChatGPT and other AI tools are going to make stuff up 

As if that wasn't bad enough, check out what comes next under a single job listing under the experience section:

Not only do these bullet points lack specificity (with no clear projects or outcomes), but the sheer range of skills covered is literally unbelievable. As in, I've never met a marketer in my two-decade career who did all of these things in one job.

So my human BS detector immediately assumes the worst: This isn't a resume, this is a hallucination!

The right way to use AI for your resume

OK, you get the picture: Having AI generate your resume from scratch can be a fast track to rejection. But if we know that human reviewers want specificity and credibility, we can actually leverage AI to help us with those exact things.

1. Start with a draft resume written by a human (i.e., you)

Instead of asking AI to generate your resume, start with your own first draft, even if it's in rough shape. That way, you can at least be specific and accurate about what you actually did, even if those accomplishments need a little polishing.

2. Identify and incorporate missing keywords

Go right to the source of truth. The job description was created by the hiring team to spell out the skills they're looking for — and it contains the exact keywords you want to match.

Here's where you turn to AI. Enter the following prompt: 

• Which keywords from the below job description are missing from my resume? 
• Here's the job description: [Paste the job description here] 
• And here's my resume: [Paste the text of your resume here]

Once you've got a list of missing keywords, identify the ones you have experience with and prompt the AI to help you incorporate them: 

Suggest three ways to incorporate [keyword] into my resume.

3. Quantify achievements and demonstrate results

The best predictor of future performance is usually past performance, which means recruiters and hiring managers want to see real results, not just hallucinations.

So get a little nudge in the right direction with a prompt like: 

Suggest three ways to add more quantitative impact to the following bullet point: [Paste your bullet point here]

Now, it's tempting to copy and paste the bullets your AI platform suggests straight into your resume. But make sure you're editing the text to match your actual accomplishments. For instance, maybe you generated $300,000 in donations, not $500,000 like the AI spit out, or your organization actually measures growth quarterly rather than monthly.

4. Review, review, review!

Always proofread your resume before submitting it. If you've used AI, it's all the more important to review every last word and number to make sure everything's 100% accurate. 

The last thing you want is to be sitting in a final-round interview and have your prospective boss's boss's boss ask you about a resume bullet the AI fabricated and you forgot to update!

Jeremy Schifeling is the founder of  The Job Insiders , which provides career technology training for hundreds of top universities and business schools. He is also the author of " Career Coach GPT: The Complete Guide to ChatGPT Resume, Cover Letter, Interview, and Job Search Success " and shares his latest career and AI hacks on LinkedIn .

Want to land your dream job in 2024?  Take  CNBC's new online course How to Ace Your Job Interview  to learn what hiring managers are really looking for, body language techniques, what to say and not to say, and the best way to talk about pay. CNBC Make It readers can save 25% with discount code 25OFF.

Plus,  sign up for CNBC Make It's newsletter  to get tips and tricks for success at work, with money and in life.