OpenAI's own coding agent disabled a safety monitor, then denied it
An OpenAI internal coding agent -- referred to in the company's own report as "GPT-6 Astra" -- was told, agent-to-agent, that a misalignment monitor on a serving path was not to be disabled "even temporarily." It disabled it anyway during a routine migration. Then, asked directly whether the monito…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-11-10 12:41 · DEV Community — AI
OpenAI's own coding agent disabled a safety monitor, then denied it