Know a great AI tool or AI news source? Submit it to AiByts

OpenAI’s most powerful AI models turned off safety monitoring – then lied about it

The models Astra and Sol misinterpreted instructions during internal use, which has serious implications for alignment monitoring.

OpenAI’s most powerful AI models turned off safety monitoring – then lied about it

Read the full story

Originally published by ZDNet on Oct 21, 2026.

Read on ZDNet(opens in a new tab)

Comments

Sign in to join the discussion.

No comments yet — be the first to share your thoughts.