Learning From Human Preferences
AI Safety Fundamentals: Alignment
00:00
Learning From Human Preferences on the OpenAI Blog
Learnings from feedback do better than reinforcement learning with the normal reward function. Our algorithm's performance is only as good as the human evaluators' intuition about what behaviors look correct. We think techniques like this are a step towards safe AI systems capable of learning human-centric goals. If you're interested in working on problems like this, please join us.
Transcript
Play full episode
