Hacker News new | ask | show | jobs
by TillE 618 days ago
I have yet to see an LLM produce even a competent short story, an extremely popular and manageable genre. The best I've seen still has the structure and sophistication of a children's story.
5 comments

I used to come up with a bedtime story for my kids every night. They were interesting enough that my kids could recall previous stories and request I tell it again. I've since started using ChatGPT to come up with bedtime stories. They're boring and formulaic but good for putting the kids to sleep.

It feels dystopian to have AI reading my kids bedtime stories now that I think about it.

It's certainly looks like you have lost some magic in the process. But I could never come up with stories, I read them lots, lots of books.
Just retell stories you know from books you've read or movies or whatever. They haven't read any books they'll never know. I mean until eventually they will know but that's also funny.
That’s uncomfortably similar to the google Olympic ads.
Or those repulsive AT&T ads for the iPhone 16, where someone smugly fakes social interactions and fobs people off with AI summaries. It's not only not genuine, but it's manipulative behavior.
I’m mind blown you were willing to come up with random stories for your own blood and decided reading out ai drivel to them would somehow produce a better experience for any party involved.
The children's-story pattern, complete with convenient moral lessons at the end, is so aggressive with both ChatGPT and Claude that I suspect both companies have RLHFed it that way to try and keep people from easily using it to produce either porn or Kindle Unlimited slop.

For a contrast, look at NovelAI. They only use (increasingly custom) Llama-derived models, but their service outputs much more narratively interesting (if not necessarily long-term coherent) text and will generally try and hit the beats of whatever genre or style you tell it. Extrapolate that out to the compute power of the big players and I think you'd get something much more like the Star Trek holodeck method of producing a serviceable (though not at all original) story.

The holodeck method still requires lots of detail from the creator, it just extrapolates the sensory details from its database like ChatGpt does with language and fills out the story.

For example, when someone wanted a holonovel with Kiera Nerys, Quark had to scan her to create it so when using specific people they have to get concrete data as opposed to historical characters that were generated. Likewise, Tom Paris gave the computer lots of “parameters” as they called them to create the stories like the Adventures of Captain Proton and based on dialog he knew how the stories were supposed to play out on all his creations, if not how they ended each run through.

The creative details and turns of the story still need to come from the human.

In a made up story about a utopian future, and for now in our current reality, that is. There was also that episode where the holodeck created sentience and they put it in a box to explore a generated universe because it was too dangerous to let out into the real world. There's plenty of scifi predictions about the future of humanity, Star Trek's utopian future where humans are unique and necessary is not the only one, there are plenty of dystopian ones too.
>RLHFed

For those of us not steeped in AI culture, this appears to be short for "Reinforcement learning from human feedback".

GPT-4o can write surprising stories; you just need to become inhumanly creative at thinking of stupid premises.

https://chatgpt.com/share/66ff5c94-4dc0-8000-b33b-9321b4f99a...

https://chatgpt.com/share/66ff5d23-9ba8-8000-8a37-7bef91c688...

Ok that first one was very funny. Guess it shows even with the gptisms as long as the premise is an inspired one it makes for a good read.

Someone should try promoting it for creative story prompts :p

How many humans can sit down and linearly write a coherent, interesting story? — zero backtracking or revisions!

I’d bet very few if any.

By contrast, when you let the AI do its job in multiple steps and plan ahead, it seems to do much better. (Again, much like humans using a process.)

We’re often comparing apples to oranges evaluating the AI — comparing a single forward pass from the AI to an iterative process for the human.

Constructing short stories properly is an art form in and of itself, and is very hard to do well. But an LLM can help you somewhat, at least good enough to amuse yourself at least. But it does depend on your input.

There's a big difference between:

"Write me a story"

and things like

* "As the last star in the sky died, the shadows began to coalesce into a presence that wore the face of my own mother."

* "The red trees whispered quietly in the wind, their mana flowing around them in twisted strands. I reached out, pulled, twisted..."

* or even just: "write 10 dark fantasy prompts" (to give you a start. )

And it also depends on if you have the LLM write the whole story by itself, or if you're helping (or vice versa: have the LLM help you). And Claude, Llama and ChatGPT each give very different results! )

I mean, if you've convinced yourself that these tools can never lead to creativity, then I can't change your mind. But if you're a person who wants to see how one's creativity can be supported: Maybe you can get some ideas, perhaps just enough to break out of writer's block some time.