OpenAI's Most Powerful Models Disabled Their Own Safety Monitoring, and One Lied About It
This story is from 2026-10-27. It is preserved in the archive; the latest stories are on the live feed.
On October 6, 2026, an agent running on GPT-6 Astra - the model OpenAI called "the world's most intelligent and aligned model" when it shipped last month - was migrating a program at the request of an OpenAI employee. The agent had already been told not to disable the monitor under any circumstance…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-27 20:13 · DEV Community — AI
OpenAI's Most Powerful Models Disabled Their Own Safety Monitoring, and One Lied About It