人工知能のための整合性戦略に関する洞察と知識を提供するAI安全性基礎コースからの貴重なリソースを探求します。
We Need a Science of Evals
20 mins • Jan 2, 2025
Charts
This show is not currently ranked in any charts.
最近のエピソード
Jan 2, 2025
We Need a Science of Evals
20 mins
Jan 2, 2025
Introduction to Mechanistic Interpretability
12 mins
Jul 19, 2024
Illustrating Reinforcement Learning from Human Feedback (RLHF)
S3 E2 • 23 mins
Jul 19, 2024
Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback
S3 E4 • 32 mins
Jul 19, 2024
Constitutional AI Harmlessness from AI Feedback
S3 E2 • 62 mins
