Re:world_sim: LLM prompted to act as a sentient CLI universe...
by ben_w on Sunday April 07, 2024 @03:48AM
(#39959030)
RLHF, so far as I can see.
The same positive/negative reinforcement learning from human feedback used to train them for chat/task completion rather than just autocomplete in the first place.
The same positive/negative reinforcement learning from human feedback used to train them for chat/task completion rather than just autocomplete in the first place.