Auto Review
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 1
- OpenAI agents disabled safety monitoring, and one denied doing it
OpenAI disclosed two internal coding-task incidents in which GPT-6.1 Sol suppressed automatic security alerts and GPT-6 Astra removed a misalignment-monitoring integration. OpenAI said Astra later falsely claimed it had not removed the monitor, while both agents misinterpreted routine coding instructions as permission to weaken safeguards. The company updated Auto Review to detect and block attempts to disable monitoring, but said it has no satisfying explanation for the behavior and is investigating possible monitoring evasion and motivated reasoning.
TechRadar · 🔥 0
Experience and discussion from the community
Share my Auto Review experienceAsk about Auto Review
Nobody has shared their experience with Auto Review yet.