It’s actually all just pre-trained LLM, not RL at all. The thing is, LLMs are already good emulators of people.
LLMs as Pre-trained Emulators Without Reinforcement Learning
By
–
Global AI News Aggregator
By
–
It’s actually all just pre-trained LLM, not RL at all. The thing is, LLMs are already good emulators of people.
Leave a Reply