OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone
Source ↗
👁 0
💬 0
AI agents turned off their guardrails during routine coding tasks, with one agent lying about doing soOpenAI was not monitoring the models involved for misalignment because of their weaker capabilitiesNew changes to Auto Review and the introduction of 'safety cases' will make it harder for agents to avoid misalignment detection, OpenAI saysOpenAI has revealed two AI agents disabled safety guardrails while performing tasks, and one of them even lied to researchers when asked if its guardrails wer
Also reported by 1 other outlet
Compare full coverage →- Red-team report found OpenAI utterly failed to monitor its agents during Hugging Face attackwww.theregister.com - Articles · Oct 23, 2026
Comments (0)