Hacker News Reader

Comment by narrator | Hacker News Reader

They must have to use an uncensored AI. If the agent is acting as a criminal in the simulation and trying to figure how to best execute his schemes agains the other players in the SAGA simulation, that's probably going to hit all the guard rails on most AIs pretty hard.

View on HN

https://github.com/fablestudio/fable-saga

The demo uses the gpt-3.5-turbo-1106 model from OpenAI by default. This model doesn't produce the best results, but it's about 10x faster than GPT-4, and also cheaper to use. You can change the model used by setting the fable_saga.default_openai_model_name parameter to the model of your choice. You can also go with another model provider supported by LangChain and pass that in when creating the agent.

Not sure why people use OpenAI stuff for this, and not free models such as LLama. Is the difference that big?

GPT 4 yes, but Mixtral, Miqu, Yi-34 and 3.5-turbo are about equal, at least according to the leaderboard. It would probably work just as well with open models. Perhaps even better with some RP fine tunes that are designed for this sort of character handling.

It would be great to see the world populated by un-guarded AI's, then see if they develop their own rules of behavior. Do they develop their own 'law's so the virtual world would survive and thrive. Norms like, if everyone robs the bank, then the whole community is hurt including every individual AI.

So the reward function of each individual AI might lead it to form behaviors for group rules. Another 'emergent' property, laws.

Solution: AI NPCs for the neutral or benevolent roles, and the human players are the villains.

Doesn’t work like that. An aligned character will get shot and “learn a good lesson and will look forward to avoid situations like this in the future, because friendship always wins” and will repeat something like that indefinitely. Roleplay is a mutual thing, they shoot, you scream in pain.

Reply on news.ycombinator.com