BlueDot Impact

AI Safety Fundamentals: Alignment

Explore valuable resources from the AI Safety Fundamentals course, offering insights and knowledge on alignment strategies for artificial intelligence.

Listen on Apple Podcasts

We Need a Science of Evals

20 mins • Jan 2, 2025

Recent Episodes

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

Language
English
Country
United Kingdom
Feed Host
Request an Update
Updates may take a few minutes.