Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

adventure-of-penelope.vercel.app

Post reply on HN
Print view View original

181–190 of 415 posts

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#181

Post by wildrhythms »

robertlagrant wrote: post #146
makoto12 wrote: post #141

I hate this so very much. Automating creativity is so gross. Never mind the fact that these models are trained on stolen artwork and texts.

If a person learns how to paint expertly by looking at (and even copying, stroke for stroke) paintings, would you consider that immoral, and those paintings having been stolen? If not, what would you say the difference is?

The difference is that a human made the artistic stroke-for-stroke reproduction through human skill and expertise. Even a counterfeit painting is an exercise of perception and interpretation. The value is in the human's hand in the output.

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#182

Post by quonn »

throwaway675309 wrote: post #25

I hate to be the contrarian voice, but I really don't like where things are headed with these types of assistive tools. I like the idea of using it partially to help complement some effort that you've done yourself, but the idea that you're using both an LLM to produce the story and a diffusion model to produce the pictures makes the entire piece of work almost devoid of individual effort. Using them to produce a pri…

It can easily be polished and that _does_ take work. So it's not zero effort. Yes, there will be a lot of generated content and that will probably lead to a recalibration of what's important and what not (in life, work, art, etc).

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#183

Post by dalbasal »

svantana wrote: post #150
makoto12 wrote: post #141

I hate this so very much. Automating creativity is so gross. Never mind the fact that these models are trained on stolen artwork and texts.

On an emotional level, I totally agree. But as a developer of creative tools, I've been trying to make sense of what's good and bad in this field. Arguably, all creative software is at least partially automating creativity (photoshop, ableton etc). But my conclusion so far is that the gross part is when the user inputs a vague request and a finished product comes out. Contrastingly, if the user can make continuous ch…

It usually trends to the way over time.

When you're demonstrating or studying a tech (like we're doing with gpt now), there's a tendency to go "here's what it can do." Once people start using it for more mundane work, the focus becomes "here's what I can do with it."

It probably doesn't matter what children's stories language models can write themselves. It matters what stories people can write using them. Same for software/graphic design/law/etc. These are just tech demos.

This becomes clearer once demos play out. 2 years ago, scripting a philosophical debate using language models felt like AIs expressing their opinion. By now, we're past that.

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#184

Post by tonetheman »

nstart wrote: post #21

There is a market, at least within south east asia, that mass produces stories like aesop's fables, and regional folklore. The books produced are thin 2minute reads and are available for purchase for less than 1 USD usually. It's not surprising to see grammatical and spelling errors slip into the prints of some of these books. The artwork is basic and while stylistically more consistent than OP's effort, it's entirel…

[dead]

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#185

Post by quonn »

marcell wrote: post #74
safety1st wrote: post #40

Earlier quoted context omitted.

It doesn't look to me like the cost of production was zero and the content really wasn't bad. For anyone who didn't read to the end, the author (operator?) explains his process: > I typed a series of prompts to ChatGPT to get it to write me a story with the following plot: > Once upon a time there was porcupine. Every day, she baked a loaf of bread. One day the loaf disappeared. Because of that, she had too much butt…

> I doubt it was a trivial endeavor. Per authors comments above, it was indeed a trivial endeavor: a few hours to tweak the prompts and a few hours to make the site. Compare to the most basic children’s book, which would take at least 10 hours to illustrate for a professional (10 picture times one hour per picture).

So then found objects and ready-mades are also a trivial endeavour? These authors published one of the first stories like that and that alone makes it not trivial.

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#186

Post by k__ »

harshaw wrote: post #179

I keep coming back to the fact that these technologies enable people to create simulacrums of high quality content quickly - but that shows because of the obvious short comings as identified by other posters. If I gave myself a week to write a children's book using these tools with a human editor loop - could I create (or perhaps someone more talented) a great book? That seems possible. This seems like it was created…

Take all the work of writing a book.

Factor out the creative tasks.

Focus your work on the creative tasks and let the AI do the rest.

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#187

Post by pharke »

2muchcoffeeman wrote: post #135
thih9 wrote: post #127

Earlier quoted context omitted.

Then again, “things got slippery” can be used metaphorically; and that meaning did appear in the story (mischievous Sparkles).

Well it’s a kids book. So I’m not sure it should be heavy on metaphors. It’s really not great though. On the last page the hedgehog becomes huge. And it makes no sense. Why was there too much butter? Why was some random girl in the house. How does butter make bread disappear? Why is one character a hedgehog and the other a human girl?

I'm of the opinion that all kids books should be heavy on metaphor and allegory and all of the other important and joyful aspects of language. Restricting children to books that have been "written at their level" or "made easy to read" is doing them a disservice. It's no wonder so many people grow up to be seldom readers if their first exposure to reading is saccharin pablum that presents no challenge, no meaning, no mystery, and no danger. A proper children's book should be one which an adult can also read and enjoy if they give way to that childlike wonder that still lives within them.

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#188

Post by quonn »

drpixie wrote: post #34
throwaway675309 wrote: post #25

I hate to be the contrarian voice, but I really don't like where things are headed with these types of assistive tools. I like the idea of using it partially to help complement some effort that you've done yourself, but the idea that you're using both an LLM to produce the story and a diffusion model to produce the pictures makes the entire piece of work almost devoid of individual effort. Using them to produce a pri…

Another strong agree. These models don't understand anything, they just produce something that is statistically (at many levels) close enough that it will fool most of the people, most of the time. For those that are increasingly happy to live in, and raise their children in, that fake and simplistic environment, I suppose it's their call. But reading/watching/living in that simpler, dumber environment can't be good…

And what the brain produces is not something that is statistically (at many levels) close enough that it will fool most of the people, most of the time?

Have you looked into even basic neuroscience research or perhaps at least personally known someone with, for example, dementia? It would perhaps teach you something about what the mind is and isn't and what we know and don't know and how perhaps AIs might fit in this story.

Just handwaving because it's "just statistics" is not useful.

As for the environment - well, I have my opinion on social media and online content and even most print content and most books. Will AI make that worse? Yes. But it's already bad enough that this is not a meaningful change. The good stuff has always been accessible and for a long time.

Re: Show HN: I “wrote” a kid's book with ChatGPT and Midjourney

#189

Post by wildrhythms »

Jolter wrote: post #152
moonchrome wrote: post #87

How do you get a layer of butter on your kitchen ? Not a native English speaker so maybe this sounds natural to people - but to me it sounds like bad wording. It paints the wrong picture and is not kids friendly wording IMO.

What about it seems “not kids friendly” to you? I don’t see the problem.

'On your kitchen' is not something most English speakers would say; they would say 'in your kitchen'. Otherwise it seems like the butter is 'on top of' the kitchen, like on the roof. And instead of 'your kitchen' it would be 'the kitchen', since the story takes place at the house of the characters in the story and not the reader's house. Also usually children's books are much more descriptive: "Butter went everywhere! On the ceiling, on the floor, on the refrigerator, on the toaster..."

And to the point of not being kids friendly, imagine your child has this book read to them, and you find the next day that they've illustratively covered your own kitchen in butter... Most children's stories are written in a way that spells out danger or bad behavior meaningfully.

Post reply on HN