The Vergecast - AI can be your writing buddy, your blogger, or your Dungeon Master

Episode Date: September 28, 2021

For the next four Tuesdays, Verge senior reporter Ashley Carman will explore how artificial intelligence and machine learning are shaping the future of a variety of industries. In this episode, Ashley explores the wild world of AI writing and storytelling to find out if her job is in jeopardy. Is AI ready to replace seasoned writers or experienced reporters? Guests include Nick Walton (co-founder and CEO of Latitude), Samanyou Garg (founder of Writesonic), and artist K Allado-McDowell. This podcast was made by producer Liam James, senior audio director Andru Marino, senior reporter James Vincent, and senior reporter Ashley Carman.  Learn more about your ad choices. Visit podcastchoices.com/adchoices

Support for the show comes from Retool. Too many companies run critical operations on duct taped spreadsheets, Slack workflows, and whatever else they could cobble together. Not because they want to, but because building internal tools means weeks of waiting on someone else's backlog. That's where Retool comes in. Build custom internal tools just by describing what you need. Prompts something like,

Build me a revenue dashboard on our Salesforce data. And Retool actually builds it on your company's data, in your cloud with enterprise security built in. Go to retool.com slash vergecast. We all need to retool how we build software. Hey, Virchcast listeners, it's Nealai. For the next few Tuesdays in the Vergecast feed, we're running a mini-series we made

about the different uses of artificial intelligence and machine learning all over the place. All hosted by Verge senior reporter Ashley Carman, who is here now. Hey, Ashley. What's up? It's episode three, the penultimate episode. This is like the Game of Thrones style, big finish. What's going on in this one? So we've talked about audio, voice clones. We've talked about

video. Now we are talking about text generation. This is the one that's going to replace you and me and our jobs as writers. Exactly. Very near and dear to both of our hearts. I don't think any robot can replace me. Or you or anyone. But what's going on in this episode? So we're talking about a technology called GPT3 and some of the use cases for it and how it might also be used in the future. Give me an example. So like authors who are actually using AI to help them, write a book, like publish a book that's co-written by both a human and AI. Like a writing buddy, like a robot writing buddy. Yeah, kind of, kind of like a robot writing buddy.

This is my dream. All right, let's listen to it. Episode 3 of the Vertcast's AI series, roll the tape. We've always been interested in talking to computers to sit down and have a conversation with the machines that do so much in our lives. Unlike our previous episodes on speech synthesis, this doesn't necessarily mean audio, but being able to chat with humans is a hallmark of artificial intelligence. The most famous test of AI capability, the Turing test,

is one in which a computer tries to convince someone that it too is a human, based on nothing more complex than a conversation. Despite this, teaching computers to converse is extremely difficult. One of the earliest examples, a text-only AI therapist designed in the 1960s called Eliza, worked by asking the same basic questions over and over. Eliza is a computer program that anyone can converse with via the keyboard, and it'll reply on the screen. We've added human speech to make the conversation more clear. Men are all alike.

In what way? They're always bugging us about something or other. Can you think of a specific example? In recent years, though, artificial intelligence has made huge improvements in our ability to generate text. You've likely already seen some of these new capabilities in Google's suggested email replies, or iMessages autocomplete. But this is just the beginning, and not only is AI able to hold more convincing conversations,

it's helping to write stories, articles, and even play games with us. I'm Nick Walton, co-founder and CEO of Latitude, and we're the creators of AI Dungeon. AI Dungeon shows what these new AI text generation systems are capable of. Think of it like an old school choose-your-own adventure book, but instead of picking between a small number of predetermined actions, you can do pretty much anything you want. Just type in what your character does next,

and AI Dungeon will continue writing the story. It's dynamically made on the fly adapting to whatever actions you choose. So you could meet a dragon, and instead of fighting it, decide to give it a cupcake and become best friends and open a bakery shop, or any number of infinite possibilities. AI Dungeon works in a number of settings, from classic swords and sorcery

to detective stories in cyberpunk adventures. The system is not perfect, at storytelling, though, it can't sustain longer complicated plots and will forget the name of characters. It's like an improv partner with a limited attention span. It works so long as you keep the story going in new directions. One was early on when I was playing and I met this band of goblins and I was like, oh no, they're going to attack me. And so what I decided to do instead was tell them I teach them to play instruments. And so they let me come into their band and I taught them how to play instruments. and we eventually became this traveling musical group

that we would tour around the kingdom at different festivals playing music, and we eventually became activists for human orca quality and got invited to play for the king, and I eventually retired and wrote books. And I was like, this is something that would never happen in any other game, this kind of flexibility. This kind of text generation leads to adventures in the game that could not easily be replicated with your typical tabletop RPG.

Nick shares with us a time where he was on a quest for a magical book in AI Dungeon. And then I started to read the magical book, and, like, the AI could generate an entire magical book and system just through my play. Like, I could read it, and it was generating the pages of the magical book with, like, a very coherent magic system. And I was like, this depth that it can go to

and the extent to which it can make the world feel alive just kind of blew me away. Nick says he thinks programs like AI Dungeon will become much more common in the future, used by writers of all sorts to create story ideas and dialogue. And though we worry about software taking our jobs, he thinks this partnership will be mutually beneficial, a collaboration between human and machine. A script writer might be able to give a bunch of ideas for what a script might look like to an AI. The AI can be like, hey, what if we

did this or what if we did that? And the writer takes that and refines it and changes it. And so there's this collaborative partnership where they work together to make things that aren't really possible on their own. Where might we start to see this technology making an impact first? Maybe in video games where open world environments contain hundreds of individual characters with thousands of lines of dialogue reacting to the world around them. AI could help generate this script on the fly, fleshing out these worlds so they feel even more real. The amount of detail you have to write becomes so overwhelming that there's just a limit to how much humans can do that.

But you can imagine having a few humans who are kind of the creative directors who say, this is the world I want and really are shaping that. but then it lets an AI fill in all the details and make the world feel alive and scale that content. So there's a level of content that never really runs out, essentially, that the player can continue to find and be new every time. What's powering these programs, though? And why have they gotten so good in recent years? The answer lies in a new sort of machine learning architecture that's particularly adept at understanding the relationship between words. These systems are known as large language models.

and all the big tech companies are building them, including Google, Microsoft, and Facebook. They work by analyzing massive data sets of writing, which they study to discover what words tend to appear next to one another. Based on the strength of these relationships between words, they can then generate their own text. For example, if you're writing a list that starts, I need to buy eggs and flour. Then the next word is more likely to be milk than bricks. Or if you begin a sentence with the quote, a long time, time ago, then the words next are quite likely to be in a galaxy far, far away. Here's Nick again, who uses a large language model called GPT3, licensed from Research Lab OpenAI

to power AI dungeon. The best way I can describe it is it's like those word predictors on your phone. So your phone has these algorithms that looked at historically, you know, maybe things you typed or other people typed, and what word came next? and it suggests those words. So GPD3 is just like that, except scaled up its intelligence 100,000 times. So then it can generate not just like the next word,

but it can do that 500 times and have a whole paragraph story that actually makes sense and is interesting. It's worth stressing just how big these programs are and how quickly companies have been able to improve on them by simply adding more data and computing power. The size of these language models is measured in how many parameters

they have, or connections within their networks. GBT2, which was released in 2019, had 1.5 billion parameters, but GBT3, released the following year, has 175 billion parameters. That's over a hundred times bigger. These programs are also trained on huge amounts of text. GBT3, for example, learned the connections between words by combing through a pretty decent chunk of the entire internet. It's hard to give a totally accurate estimate of how big it's

training data set was, but we know that all of English Wikipedia, spanning some six million articles, comprises only 0.6% of the total size. There's this really interesting thing where when you train it on so much data and with such large, smart models, it captures all these patterns that are actually really complex and interesting, and there's a lot of information in those. The problem, though, is when you train something on texts scraped from the internet, and internet, it picks up some nasty habits. The first of these is that large language models very much reflect the biases of our society.

Because they've learned how to write in part based on toxic screeds online, they therefore regurgitate harmful stereotypes about gender, race, and religion. They spout racist and sexist nonsense with very little prompting. Some of this output can be filtered, like any hate speech online, but it's impossible to be certain that these biases have been eradicated on a more fun. fundamental level. You have to ultimately follow a multi-pronged approach in doing this. The analogy I make is the human brain can generate lots of things you could say, but there's

also a part of your brain that's like, better not say that, right? Like there's this filter component that takes the possibilities and decides what things are good to say or not. So I think systems like that are important as well. Another problem is that language models are often factually unreliable. They can answer basic trivia questions, but never with 100% certainty. because they have no way of distinguishing between fact and fiction. All they know is how probable it is that certain words appear together. A lot of the time, this is good enough to produce the

right answer. But it's not something you necessarily trust if you were doing important research. It's also one reason why AI Dungeon is a good use case for these systems. No one cares about facts when you're writing fiction. What about the world outside of dragons and orc rock bands, though? What else can these models do? Well, many companies now offer AI language models as multi-purpose writing tools that can tackle a number of tasks, from writing product descriptions to blog posts to student essays. You know, we have like quite a different set of target customers. That's Samanu Garg, founder of Wright Sonic, one of a number of new startups that offers this

sort of tool. So just for the article writer, if we are talking about content writers and copyrighters use it a lot, they just put in their topic and they get like an initial draft, which is like 60 to 70 person there, and then they improve upon that, like add their own links or references and so on. Sam tells us that he relies on both GPT3 as well as a number of home-brewed AI models to meet his customer's demands. One of the most popular use cases, he says, is for shopping sites, which are looking to produce a lot of written content quickly and cheaply. They basically have their own Shopify stores or Amazon stores, and a lot of them use the product description tool because it really

helps them generate product descriptions at scale because, for example, some of the companies that recently approached us, they have like 10 million product descriptions on their website. So it's not possible for a human to, you know, write that many and to maintain that brand quality slash tone. So that's where it kind of comes in handy. So we are building some custom models for them. Another service he offers is creating blog posts and articles for websites. It takes a little bit of input from the user, though. You can't just click a button and generate a perfect post right off the bat. So basically, article writer consists of four different steps right now. First one is like you input your topic and comes up with the actual titles and ideas for your potential blog post. So for

example, if you put in, you know, productivity app, it would come up with, let's say, 10 productivity apps that will make your life, you know, amazing or something like that. And then we generate the intro based on what you provided in as a title. And then the third part is the outline, where it generates all the sections in the article, and then finally it kind of writes all those individual components and then assembles it together into like a long article. To create these outputs, Sam says he had to fine-tune his language models. That means finding training data that's similar to the output text.

In other words, he shows the AI model the sort of writing it needs to produce itself. For the article writer, that meant he had to scrape a lot of data from new sites, including one that might be familiar to Virgil listeners. We scrape tons of top websites on the internet from all sorts of different industries. You know, obviously tech websites like verge.com and medium as well as other WordPress blogs as well as other sites in different industry like fashion industry or lifestyle industry and so on.

Are AI writing tools like this going to replace writers? Not directly, says Sam. He thinks they'll be more like cloud. used to jumpstart new ideas and create the bare bones for pieces of writing. We're already seeing the first steps of this process happen, with tools like Google's Smart Reply and Smart Compose. But collaborating with AI writing tools can go so much further than just firing off some boring work emails. A number of writers have started using these tools to create new forms of artistic impression,

hybrids between computer and human fiction. One of the most interesting of these is Pharmaco AI, a book-reacto-a-I, a book written by the artist and writer Kay Alato McDowell and GPT3. I definitely gained a new set of reference points and structures for thinking through that experience of writing pharmaco AI. It's been described as a quote-unquote hallucinatory journey into selfhood, ecology, and intelligence. But, as Kay tells us, it started life as a conversation between them and a computer, just like those first interactions with the therapy bot Eliza in the 1960s. So the process of writing was very conversational,

but basically what I would do is I would write into a text field. I would write a prompt. Sometimes that would be several paragraphs, sometimes it would be very short, and then I would generate some text from the prompt. I created some rules for myself. One was I would edit the output as it was coming out, and if I wasn't interested in what it was saying,

I would cut that part and regenerate. So I kind of compared it to pruning a plant. and once I had decided to keep something, I would keep it and I would add to that. But I would never go back and rewrite the beginning because I was really interested in seeing how the thoughts developed through the exchange and leaving a record of that back and forth. The book itself is not a novel. There's no plot or discernible characters apart from K and the AI. Instead, it reads like a series of meditations on the nature of the self and creativity

and how we generate meeting from writing. The text takes on many different forms. Sometimes it's poetry, sometimes it's dialogue, and sometimes it reads like a revolutionary manifesto, a guide for the future of our relationship with computers. Kay says they actually wrote the book over the space of two weeks while hoping to finish a completely different project. It was very much serendipitous and not something I had planned,

so I ended up publishing a book, but not the one I had been working on for years and thought I was going to finish. In the physical version of the book, the text written by K and generated by AI are printed in different typefaces, allowing the two forms of writing to appear like dialogue. But as K explains, the project also blurs the boundaries between human and machine intelligence. One of the big concepts in the book is the idea of emergence or being part of a larger ecosystem than just the individual human or the machine. So it was very hard to say sometimes where the ideas were coming from. I mean, as it is often with writing, but in this case, there were two actors,

so you could sort of say, well, it came from this person, it came from the machine. But actually it was a little bit less clear than that. And especially when I would start to have dreams about the imagery, you know, I was like, yes, this is coming from me, but it's coming from a part of my mind that isn't fully conscious, or, you know, it's coming from a part of my mind that processes information differently. Is this sort of interaction with machines something that will all experience in the future? Having conversations with AI and not knowing whose ideas are whose? Kay says it's possible, but points out that the experience of using AI writing tools in the workplace

is very different to the sort of self-reflective writing process they went through to create Pharmaco AI. Ultimately, though, they say the emergence of these tools raises new questions about how we think about our own intelligence. This question of, is the system extending me? Am I extending it? Where is the agency? How do I even determine agency in a human-to-human-human-to-human relational scenario? Or a human-to-animal or human-to-plant relational scenario, it starts to push on our preconceived notions of the bounded self. I've always thought that treating AI as a mirror is the most clear way to make the point that these statistical systems, we're predicting. systems are going to give us back ourselves at the individual level. So whatever we put in is what we're going to get back out. Kay's experience using GPT3 to write a novel seems like a pretty extreme and unusual interaction

with these AI systems. But is this sort of work going to become more common in the future? How are text generation tools going to be used in everyday life? And where do you draw the line between your ideas and the computers? We're going to take a break. But when we're back, you've heard from him before, James Vincent's senior reporter at The Verge who specializes in machine learning and AI will be here and we'll answer all the big questions we have, like whether machines will replace me and my reporting in the future. We'll be right back.

Support for this show comes from Shopify. Every thriving, successful business has to start somewhere. A good place to start is a relatively simple question. What if, given the right tools, I really put my all into this. One tool that can help grow your sprouting business to new heights is Shopify. Millions of businesses around the world rely on Shopify for e-commerce. They offer a host of helpful tools you can take advantage of, from payment processing to analytics to website design.

Their design studio includes hundreds of templates to help you create the exact website you've been envisioning for your business. If you're wondering, what if I need help? Then no worries, because you're never left to fend for yourself. Shopify's award-werectuary's award-werect. customer support is available 24-7. It's time to turn those what-ifs into a thriving business with Shopify today. Sign up for your $1 per month trial today at Shopify.com slash vergecast.

Go to Shopify.com slash vergecast. That's Shopify.com slash vergecast. Hello, we're back and James Vincent is here. Hello, James. Hi, Ashley. Pleasure to be back again talking. more AI, machine learning, but I love it. We're talking about text generation, and as I always say, I'm here to have you level out our thinking here.

So, when you're thinking about text generation and AI and all of that industry, what excites you about the field? What are you skeptical of? Give us the raw take, as I always say. It is definitely an exciting field. It's one that's been moving very quickly, and like the voice synthesis has made, like, serious, tangible improvements over. over the last couple of years. And like the text models that we have now compared to the ones we have had a decade ago are just so much better. And people didn't really imagine the improvement would be this quick. But as the improvement has sort of sunk in over the last couple of years,

we're also finding more about the limitations of these systems, both in terms of, you mentioned earlier, some of the biases they have, the fact that they're not factually accurate or they can't, it's difficult to verify that they're factually accurate. But there's also this idea of meaning. It's a tricky thing. It gets a lot of people bogged down. It gets me very bogged down.

It's like, do these systems understand language? And does it matter if they do or if they don't? And it's sort of a question no one has any answer to. It's like, as long as they sound plausible in what they're coming up with, does it matter if they understand what they're saying? And then some people say it does hugely matter because it means they don't have a model of the world like humans do. So they don't know when they're saying something that does. doesn't make sense. So I feel that's something that we're just beginning to explore, and that will be, as these systems appear more in practical consumer commercial applications, we're going

to bump up against more of those limitations, and we're going to see more problems with these systems, I think. Yeah, it's interesting. I mean, we're skipping ahead a little bit here, but it's top of mind as a person whose job is mostly writing. But we talk a little bit about news articles and how it could be used to create blog posts and things like that. And I do wonder if them not being able to be factually accurate does affect whether you could use it for sort of these like news posts and things like that just because I feel like even if it is sort of like routine to write a news post you still have the reporter being like I know this to be true and I'm going to actually double check it and whatever else so I do wonder if actually this could even replace news writers really I feel like it really depends on what sort of news you're talking about I've played around with a bunch of these different systems and and see what it comes out with

It comes out with garbage. It comes out with like something that just doesn't work. I mean, there are huge limitations. These systems can't research. They can't sort of Google the stuff for you and synthesize all these sources. They can't do new information. They are, you know, they're trained on old data. So they fundamentally don't have this new stuff that you want.

They can, though, do wrote writing, really sort of buy the numbers stuff. And where we've seen newsrooms adopt AI writing tools, not necessarily GPT3. and its ilk, but sort of even earlier writing tools, they've used them for stuff like there was a tool that did automated earthquake announcements. So it was hooked up to some sort of meteorological data set. And when that registered an earthquake of a certain magnitude in a location, it wrote that up. And it just sort of like it had a form, basically, and it punched in the numbers and it punched in the location, and it published it. And so there are things like that where AI can definitely write some basic. formulaic stuff for, say, movements in the stock market, for sports results, for weather. But when it comes to writing anything new, it can't do it. It can do it with a little bit of

help, but I think at this moment, it's not worth the extra hassle it takes for a writer. So, Ashley, your job, absolutely safe. Oh, thank God. That was the biggest question I had. Because we've really tried to replace me like in every single episode here. It's been a running theme. Yeah, I'm feeling confident coming out of this that like I will still have a job hopefully. Absolutely. So you mentioned that you've tried to use this on your own, these text generation tools. Can you give some examples of instances either where it did work really well and you're like,

this is amazing? Or if you have instances where you're like, you kind of mentioned like the news writing where you're like, nope, this isn't going to work. But others if you have them. Well, it's like you said earlier on about, you know, the AI dungeon being a good fit for it. These tools are surprisingly good at being creative or, you know, is it really creativity of its machines, who knows? I think it is because I think they come up with stuff, which is

interesting and funny. So one of the projects I was playing around with when I had access to GPT3 was for the Verge's 10 year anniversary. You know, we're doing a zine and I was coming up with some stuff for it, which includes a techno pagan spell, which I don't know if you remember, do you remember the techno pagan from Buffy the Vampire Slayer? Unfortunately not. There was, I can't remember her full name, Jenny something, who was this techno pagan witch. who was like, what if a witches were online and on the internet and blogging up a storm? So I thought I'd make some techno-pagan spells and I fed some stuff into GPT3.

And it came out with some like, some really like weird and funny stuff. Do you want to hear a techno-pagan spell written by AI? Yes. Okay, so the first bit of the spell is what I gave it. And I'll tell you when I stop and when it becomes the thing. So this is what I fed it. I said, techno-paganism is a new sort of magic that blends traditional. witchcraft with the power of being online all the time.

What follows is a techno-pagan spell designed to protect your phone from spam and improve the quality of messages you receive. Step one, and that was when my prompt ends. So you kind of set it up and you're like, right, now you've got to fill in the blanks. So this is the spell it gave me. Take your cell phone and go outside. Close your eyes, hold the device in front of you and in tone, I offer you, oh spirit of techno-pagan magic, my eternal and unending electronic connection to the net.

In return, I ask you for magic to combine my will with the will of the system. Make me impervious to the garbage that flows through my inbox. Make all messages flow together and I will choose among them what is right for me to see. Grant me the finger of the internet and I will strike at spam and cast out the spammers back into the dark places from whence they came. So that was what it wrote. And I was just like, that's amazing. I love that. Where did that come from?

That's really good. I guess I have a question which is like, what's confusing to me about how these systems are, work is so obviously when you're talking about spam, I can imagine, and you specifically said phone spam. So I can imagine that this AI has a reference point that is like people have written about how phone spam is garbage, like give me my clean inbox. Yes. Whatever. They're going to say. And I can see where it pulls those words from. But then like what's confusing to me is how it then also infuses kind of this idea of like the techno paganism

and magic. Like it somehow fuses the two. So it's like interesting to me that it's able to pull from different systems or different pieces of writing, I guess, and know that it should go together. No, absolutely. This is the wonder of these systems that all they know is the relationships between words, but they know it on such a multi-dimensional level. Like they work in this multi-dimensional space to find the relationships between them. And from that, they somehow managed to come up with this stuff.

So the thing I will add is that that wasn't the first spell that it wrote for me. And it did write some stuff that was kind of useless. not as funny. And I had to tinker around with it. There are all these different settings you can adjust and the most important one is called temperature. And it's how weird you want the response to be. So if you have a very low temperature, it will sort of follow it, you know, as boringly as it can. And it sometimes gets caught in loops and just ends up repeating the same thing over and over. And you increase the temperature and it gets more adventurous, more bold in what it's doing. So this was quite a high temperature, but it was, I think it was probably my third or fourth time getting it out of the system. So these

things aren't perfect. There is human curation and there is human selection needed to say, this is a good answer, this is a bad answer. It's not true of all things. But yeah, no, I'm the same as you. I'm like, I just enjoyed playing around with these tools. I just think they're so fun and like, I really enjoyed, for example,

Pharmaco AI. I just thought, just such a brilliant book and so, so enjoyable and weird. I wanted to do, if it's okay with you, Ashley, a little test. I was going to read off a couple of things from the book and I want you to tell me whether they were written by a human or a machine.

Do you fancy that? Yeah, yeah, that sounds good. Okay, I'm going to give you a little bit. So this is a poem, and was it written by a human or a machine? My grandfather was a machine. His bones and muscles were gears and levers, his flesh was plastic. His eyes were video screens, and he had radars for ears and wings that he would use to fly. He would count to a million, and he was a math genius,

and he knew how to make you feel smart. He was born in a factory in Detroit, and his DNA was blueprints for making cars. He had two names, one for my father and one for my mother. Do you think that was a machine or a human who wrote that? I'm going to go with human. I was written by the machine. Dang it. A machine wrote a poem about being a machine. It's really spot on. Yeah. I was trying to listen if there was words that maybe would make sense why they would be next to each other. But like if you were just having a conversation or writing, maybe wouldn't necessarily

use next to each other, but I couldn't really pick one out that seemed odd, like odd word choice. Yeah, I think it's pretty seamless. Okay, here's another one. Language is not only an act of communication. Language is the creation of experience. Language is a fractal expression of life, as life or existence is the creation of time and the accumulation of relations through time. Semiosis is the constant interaction of internal and external words, and an internal world

is created in the external world as an external world is created in the internal world. So do you think a machine or a human wrote that? I'm going to go to human again. A machine again. That's another machine. That sounded more like too philosophical. Like it was just too many questions. I was like the human must be asking these questions. Okay, let me do you one last one.

The Greek god Hermes, counterpart to the Roman Mercury, was the god of translators and interpreters. A deity that rules communication is an incorporeal linguistic power. A modern conception might read that it is a force of language from outside materiality. Automated writing systems like neural net language models relate to geometry, translation, abstract mathematics, interpretation, and speech. And it's easy to imagine many applications of these technologies for trade, music, and divination. I mean, I should guess human again just because I feel like I've guessed human for everyone, so I have to eventually get right.

but I honestly would guess AI for this one. Okay, that was human. That was human. I figured, but I'm like... You played the game right, and you got it that way. But it's interesting. Like, this is a place where I would say at least. It's more difficult to tell.

This is a definitely trickier zone to identify. Yeah. And it's, you know, it's just none of these technologies is a simple, is it, you know, a simulacchrome of humans or is it not? Or each of them has a specific way that the information is delivered. And so this is trickier to tell, but it's trickier to tell because humans have been involved in the process, whereas the synthetic speech is easier to tell,

but at the same time it's also something that can be done without human input. So I think there's weird ways to balance this stuff about how smart they are because it really depends on the context. Yeah, that's a good point. Do you feel that these tools would be useful for you? You know, if you had something that was like, here is my story headline, and it gives you sort of a brief outline and then you fill in the actual writing, would you want that if it could do that?

I feel like in my day-to-day, no, like for my specific type of writing, I don't necessarily know if the appellate, because as you kind of mentioned, and this is getting a little niche, but like just as a reporter, I feel like we're constantly updating our databases of information. Like companies get acquired, new things happen. There's a lot of context that maybe just occurred two days before or you're writing to news that just happened and you're doing a take on it or something. So I feel like my internal data set is like much more current and I need it to. accurately do my job.

Yeah. But I do find it potentially interesting for more of creative endeavors. Yeah. But I do wonder if, like, authors could use this for ideas and then just use them as their own and not disclose that an AI helped them come up with that. Or if you even need to disclose that an AI helped you and inspired you or even gave you outright the idea for something. There have been a couple of tricks that people have done like this.

There was some sort of essay written by GPT3 that got onto Hacker News. and got a lot of attention and interest and was upvoted and was presented as being written by a human. And some people were fooled by it and some people weren't. The question, again, is how much curation went into making that before it went in there.

But I genuinely think that there will be people using these tools quietly in the background and not saying anything about it. And I think it's something that is going to be a general trend we're going to see with all these synthetic tools is that there's probably going to become a new layer of prestige in the media when you say, in the future, in the future this is, when you say something is a human only product,

you know, in the same way that you buy eggs that are free range, you would buy content that is human only in its production. Oh my God. I think it's going to start creating these tiers. Will the human only products necessarily be better? Who knows? I think that will be very circumstantial. But I think they'll be sold to us as something authentic, you know?

I mean, yeah, that's such an interesting point because I'm watching Game of Thrones right now. and but watching it I'm like wow this is just so incredible that one man envisioned this entire world and like it's just mind-blowing or I think of on a much smaller scale like Bo Burnham's Netflix special he did recently inside where I was just like my god

like this man is so creative and has come up with so many like it's just such a feat you know you're just blown away by it and so if I had heard oh George R. Martin used AI here to help inspire him or Bo Burnham had AI help him kind of generate some ideas. I think that would taint it for me. It would. I'd be like, oh, I mean, this is still impressive. Like, sure, but it wasn't just you. You had to rely on like a past database of massive information to like generate ideas.

So that is a really interesting point. And I just feel like there will be shady stuff going on where people won't disclose. But I mean, so let's compare this to something like Andy Warhol. If you bought an Andy Warhol painting, would you mind that it was created by one of his assistants? And he just came up with the design and then he threw it into, you know, famously used all these assistants to make his paintings. And they were just sort of blueprints that he copied and pasted as it were. It was part of his comment on mass production and on commercialization. So actually, he sort of embraced that, made it part of the appeal. And so got over any qualms that people might have about it.

And maybe this will be something that artists working with AI are doing now. And I mean, I think it's something that you do already see now with AI artists, that they make the human machine collaboration part of what makes their art special. Yeah. And it is special because I think we're at this really weird fringe point where these worlds are colliding. And it's interesting stuff is happening. Well, I think this is a great place to stop because now I have a lot to think about. Fantastic. Thank you so much, James, for coming on.

As always, I appreciate your deep insight and wealth of knowledge. Thank you, Ashley. All righty. Thanks so much for listening to this Verge cast AI mini series. This show was made by producer Liam James, senior audio director Andrew Marino, senior reporter James Vincent, and me, senior reporter Ashley Carman. Talk soon.