Loading
Reinforcement learning with human feedback is an essential technique for aligning AI systems with human intentions and improving their usability.
“Rlhf is how we take some human feedback the simplest version of this is show two outputs ask which one is better than the other uh which one the human Raiders prefer and then feed that back into the model with reinforcement learning and that process works remarkably well within my opinion”
Lex Fridman Podcast · Mar 2023 · 1 episode · 6.8M views on this topicExtracted by a model; may misattribute who said what.