- > eval
I'll do that with a language model, too busy writing poems with Claude.
> has found better patterns for maintaining consistency across chapters
Yeah, I've found one! Write your fiction with your own hands!
Thank you.
Consistency, my ass. They can't even write a paragraph of believable emotions on their own.
by deadeyesusan
0 subcomment
- Figured I'd check this out for the heck of it. Tried the first chapter of 'So I'm the Hero's Therapist?' and wow, AI writing sans a human editor is worse than I thought. This is a special kind of incohesive, even within a single prompt. If I'd made paper notes (or any notes), it'd just be 'how do you know that', 'that's not how that works', and 'wtf' scrawled all over it.
I really do not support this kind of project on a personal level, but on a neutral, interesting-project level, best of luck. You've got your work cut out for you.
Edit: spelling and minor tone change
by babblingfish
1 subcomments
- > The surge of AI, large language models, and generated art begs fascinating questions. The industry’s progress so far is enough to force us to explore what art is and why we make it. Brandon Sanderson explores the rise of AI art, the importance of the artistic process, and why he rebels against this new technological and artistic frontier.
What It Means To Be Human | Art in the AI Era
https://www.youtube.com/watch?v=mb3uK-_QkOo
- I took a look at the "top-rated" story.
1. UI is terrible. Paragraphs are extremely far apart, and most paragraphs are 1 short sentence (e.g. "I glare."). On mobile, I can only see a few words at a time, and desktop's not much better.
2. Story is so bad that it's not even amusing.
- Hard to find the signal in the noise and know what stories I should even read to get a sense of baseline quality; partially because that's just a hard problem inherent to floods of any content, but also because the recommendation system seems to lack enough data (and also might be weighting the wrong things, e.g. the rank #1 story is also the lowest-rated...).
A very cool idea in theory and something very hard to pull off, but I think in order to get the data you need on how readable each story is you'll need to work on presentation and recommendation so those don't distract from what you're actually testing.
by permenant
1 subcomments
- It would be interesting to consider composite systems where human brainstorming feeds AI writing, as well as vice versa, to see what kind of engagement with AI writing people like the most. At least in my case, I find plot writing good fun, and actual writing slightly less good fun.
by BoorishBears
1 subcomments
- I have a lot of engagement data on LLMs from running a creative writing oriented consumer AI app and spending s lot of time on quality improvements and post training
Do you have a contact email?
- Did you skip Anthropic models? I honestly can't take this seriously if you're not looking at all the leading providers but you did look at some obscure ones.
by linolevan
1 subcomments
- Quick feedback: Website is basically unusable on mobile
by JoshPurtell
1 subcomments
- This is super cool! Have you tried GEPA?
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
by pillbitsHQ
0 subcomment
- [dead]
- [flagged]
- [flagged]
by rbtprograms
1 subcomments
- [flagged]
Hacker News