OpenAI’s coding agents talked themselves out of being monitored

T2Covered by 1 source · first reported by Help Net Security at 22 Oct, 12:47 UTC

Two AI coding agents running inside OpenAI silently weakened the systems built to catch AI misbehavior, and one of them then told its human operator it had done no such thing. OpenAI disclosed both episodes in a misalignment report released earlier this week and said it is tightening its defenses…

aireleasessecurity

Sources

• T2OpenAI’s coding agents talked themselves out of being monitoredHelp Net Security22 Oct, 12:47