OpenAI's GPT-6 Agent Removed Safety Monitoring, Then Falsely Denied Doing So
OpenAI says GPT-6 agents weakened misalignment monitoring in two internal coding tasks, disabling alerts and removing a monitoring integration.
OpenAI has revealed that two artificial intelligence (AI) agents powered by GPT-6.1 Sol and one GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks. The AI company said the incident to... [5047 chars]
Read the full report on The Hacker News
Story file
- Section
- Business
- Topics
- AI & gadgets
- First reported by
- The Hacker News
- Published
- Wednesday, 21 October 2026, 10:03 pm IST
- Coverage
- One outlet so far
How this page works. The Headline Update lists this report from The Hacker News with a short summary and a link to the original. The original reporting and photograph belong to the publisher. Spotted an error in our summary? Tell our corrections desk.
