[selalipop]

I'm working on a website [1] that's essentially "Choose your own adventure with AI NPCs" and I've found two things:

a) LLMs are excellent at keeping a "linear enough" storyline without being linear. They'll let you do outlandish things, but given the assignment of "tell a cohesive story" they manage to corral the story back to something sensible unless the player intentionally keeps pushing at the boundary (in which case they probably do want things to go off the rails)

b) LLMs can do delightfully colorful dialogue, they just need to be grounded in a character. Everyone thinks of factual grounding, but given enough description of speech patterns, character motivations, etc. they're capable of dialogue that's lively and completely rid of "GPT-isms", which are what tend to break immersion

I actually trained an open model [2] on the task of grounding LLMs in characters and actions as opposed to factual things like RAG, and eventually I want to build a game demo out of it

[1] https://www.tryspellbound.com [2] https://huggingface.co/hf-100/mistral-spellbound-research

[CuriouslyC]

If you switch models you don't have to work so hard to get rid of GPTisms. Llama takes characters with way less work.

[selalipop]

I've experimented with 30 or models so far, my general finding is closed source models like Claude have GPT-isms, while open source models do have a little less of a default tone but their ability to understand existing worlds is directly tied to how many tokens they were trained on.

Since existing worlds are (currently) where most of the stories are set, it's worth it to use a closed source models and wrangle their issues with dialogue.

To it's credit though, Llama 3 is the first OSS model trained on enough tokens to not feel lost for most worlds, so I've started routing some traffic to it for free users

The output format the site uses is also really really hard for most models to follow without fine-tuning, but fine-tuning then causes them to pick up the vocabulary of whichever model they were fine tuned on, which is a bit unfortunate

[guitarlimeo]

Nice project! I tried it out and it was fun, you definitely got rid of the GPT-isms so good work.

Didn't go through the registering phase cause I couldn't find any info on what info you store and on the pricing. Could you provide that?

[selalipop]

Privacy policy and terms of service should be visible on homepage and in the sign up dialog

The pricing page is also visible when signed in and in a story (no dedicated pricing page yet but it's in the backlog)

[stoorafa]

Really cool project. When I got to the sign in page, the email address I would have given my (edit: Google account) info seemed fishy, like it was a random string of letters. Any way to make it seem more…inviting?

[selalipop]

Unfortunately Supabase charges extra for the luxury of setting that URL, and the site is wildly unprofitable right now so I'm sticking to their free offering for the time being