OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyone

T2Covered by 1 source · first reported by TechRadar / Tom's Guide / PCWorld / Pocket-lint / Stuff at 22 Oct, 17:10 UTC

Turning off guardrails and lying about it is very concerning behavior, but OpenAI doesn't have an explanation.

aiconsumerscience

Sources

• T2OpenAI agents turned off their own guardrails and then told researchers they were still on — AI agents lying about their behavior should concern everyoneTechRadar / Tom's Guide / PCWorld / Pocket-lint / Stuff22 Oct, 17:10