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.

Original post →

More from Safety

Safety channel →