Center for AI Safety Publishes Full Syllabus for Intro to ML Safety Course
ArtificialOther · x · 2026-10-21
The Center for AI Safety has released the syllabus for Intro to ML Safety, organized into four sections: Safety Engineering (risk decomposition, accident models like Swiss Cheese and STAMP, black swans), Robustness (PGD adversarial attacks, stress tests, distribution shifts), Monitoring (anomaly detection with AUROC metrics, uncertainty calibration, transparency, trojan detection, emergent behavior), and Control (honest models, power aversion). Each lecture includes recordings, slides, notes, and coding assignments; enrollment for next semester is open on the site.
More from Safety
- METR signs off on Anthropic's risk report but experts demand quantified uncertainty and neutral evals — DKokotajlo · 2026-10-21
- Mistral CEO Arthur Mensch on European AI sovereignty, gigawatt-scale infra and AGI risk — beffjezos · 2026-10-21
- 4 of 5 tampered changes pass a green test suite — can you trust your agent's 'done'? — Weary-Information-15 · 2026-10-21
- Ben Goertzel outlines a general recipe for superintelligence 'basic drives': what it improves vs. protects — bengoertzel · 2026-10-21
- America.gov launches AI portal unifying 29,000 government sites with fraud reporting — soleio · 2026-10-21
- EvilWAF: open-source transport-layer MITM proxy that bypasses modern WAF behavioral detection — godfrey_rono · 2026-10-21