Egregoros

I have been reading up on how you make LLM-mediated chatbots that do things like TIPPING CRYPTOCURRENCY not hallucinate important values. It's not actually that hard.

@sun are you looking at the h-neuron paper, the PPO/GRPO for attention fixing, or the self-checking classification stuff? There’s a ton of work in preventing those kinds of things on all levels right now and they’re all awesome