The success of the newest GPT models relies on RL to refine the latent space inside the LLM. There's a bottleneck when using humans to refine that space.
Human based RL is used because humans know stuff about the real world and can sort language utterances by this. There's "self play" process that gives a system this sort of knowledge.
Human based RL is used because humans know stuff about the real world and can sort language utterances by this. There's "self play" process that gives a system this sort of knowledge.