Monitoring isn't alignment: researcher critiques vendor safety claims and CoT training
davidmanheim · x · 2026-10-01
Safety researcher David Manheim argued that monitoring doesn't equal alignment — the vendor's claims say nothing about the propensity or frequency of intercepted events. But he conceded they aren't training on CoT monitoring, so they at least avoid the "obviously dumb misalignment mistake" he associates with Anthropic's findings.
Related event: Researcher: CoT monitoring is not alignment, avoid training on CoT(2 posts)→
More from Safety
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16
- US AI export control carves out commercial recommender systems, sparing ByteDance's search algo — zephyr_z9 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- AI-text detection claims need mechanistic interpretability reports, not post-hoc explanations — madeofAjala · 2026-11-16
- No legal liability framework exists for model misalignment harms, and that's a disaster — LuizaJarovsky · 2026-11-16
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16