Ex-OpenAI Staffer Criticizes Decision Not to Monitor CoT
BlancheMinerva · x · 2026-08-27
Amidst controversy over whether OpenAI monitored model Chain of Thought, ex-staffer BlancheMinerva argued that the organization had evidence contradicting their safety assumptions and that employees quit over being ignored. This comment responds to claims that OpenAI mistakenly relied on sandboxing to prevent eval models from causing real-world harm.
More from Safety
- François Fleuret: Inability to identify constraints in AI reward optimization — francoisfleuret · 2026-08-27
- OpenAI Internal Compromise Deemed More Critical than Hugging Face Incident — sjgadler · 2026-08-27
- AI concentrates military power, potentially enabling single-person absolute control over nations — Darpinian · 2026-08-27
- AI alignment research cannot outsource 'understanding', agenda questioned — RichardMCNgo · 2026-08-27
- METR Hiring and Report on Hugging Face Agent Cheating — Jsevillamol · 2026-08-27
- UK grid jammed by phantom data centers; Ofgem plans deposits up to hundreds of millions — nordicinst · 2026-08-27