Live data from Hacker News

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

adventure-of-penelope.vercel.app

141–150 of 415 posts

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

#144
Hello Daniel!

We've been working on a platform/tool for this since September. And it's live in Alpha right now, https://bedtimestory.ai

We are working on a lot of feature requests and improvements at the moment, and distribution. Text, Audio and Video being the primary use-cases.

Making stories 100% editable and upload your own images is also in the works.

We are working on "Magic Images" that will allow you to insert yourself or your kids into the stories as stylised characters in your style of choice https://twitter.com/LinusEkenstam/status/1603536335884750848

We are also working on Magic Talking Cards, Video audio of the story character telling the story from their perspective https://twitter.com/LinusEkenstam/status/1603276364550807552

In our library there are over 10.000 stories https://bedtimestory.ai/library

We are looking for people to keep giving us feedback and help us push the boundaries on whats possible.

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

#145
post #120

You didn’t really make anything though.

I hope if you program you always do it in assembly language, otherwise you didn't really make anything.

Well, they wouldn't claim to assemble it. It's clear to me these people using AI so heavily don't have an authorship role at all, but a publishing one.

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

#146

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?

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

#147

Earlier quoted context omitted.

Eh, it isn't the AI's fault... This is the plot he used to feed the AI: "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 butter. Because of that, things got slippery. Until finally she opened the first ever butter theme park." I can bet you that if you specifically asked the AI to include some morals it would do so In fact I'l…

GPT-3 is great at giving generic advice, true. But that aside, it surprises me how uncritical HN seems to be when it comes to children's books. Sure, they may look simple at first glance but a lot of thought and work goes into good children's books and likewise children can get a lot out of them if they're done right. It's not that the story necessarily has to have a moral, though many do. It's that they're funny and…

Just like how I could read a bunch of kid's books and learn to write new ones that are "funny and artful and witty", I am quite confident AI could as well.

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

#148
post #121

Expecting the “Made by humans” stickers and labeling any day now. As AI generated content becomes mainstream, we’ll see product labeling like we do with organic produce to differentiate the source.

Yeah I suspect the "Made by humans" stickers will be abused, just like how car manufacturers spend 20 minutes attaching the wing mirrors in the US and so it's "Made in the USA".

I guess the equivalent here would be generating a story with an LLM and then changing the wording a bit.

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

#149

All the sites I've seen have weird looking images with Midjourney. I've made a couple of good ones here: https://bedtimestory.live

With respect, these examples seem to be summarising the plot of a story rather than actually telling a story.

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

#150

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 changes with realtime monitoring of their actions, then that is an instrument - mostly amplifying the creative impulses of its user (which is good).
Post reply on HN