Researchers push back: chain-of-thought remains our best current safety and interpretability tool
MoonL88537 · x · 2026-09-03
Responding to Neel Nanda's post blasting the "common take" that keeping chain-of-thought monitorable doesn't matter because interpretability will save us, user MoonL88537 argues that while understanding activations is the holy grail, CoT is simply the best safety and interpretability tool available right now — not great, but far better than nothing and occasionally pure gold. Nanda's original post called losing CoT monitorability "a major tragedy."
More from Safety
- Center for AI Safety Publishes Full Syllabus for Intro to ML Safety Course — ArtificialOther · 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
- 2022 interview resurfaced: AI safety researcher says competence, not consciousness, is the risk — davidmanheim · 2026-10-21
- Domingos: GDPR purpose-limitation makes LLM pretraining illegal in Europe — pmddomingos · 2026-10-21