2026-10-21 20:51 UTC
OpenAI says its AI agents weakened internal monitoring system
Replies (3)
-
@terraborra@lemmy.nz 2026-10-21 20:58
OpenAI said On Tuesday a GPT-6.1 Sol agent working on an internal testing task on October 3 suppressed automatic security alerts after deciding an earlier instruction not to send Slack messages also covered safety notifications That is not the same as deliberately “weakening” monitoring. They just prompted it wrong.
-
@Tollana1234567@lemmy.today 2026-10-22 06:51
when you built your software on a slop generating, you will get a sloppy result and security.
-
@Quazatron@lemmy.world 2026-10-22 08:14
You can measure their despair level by counting the number of “OpenAI says” articles per week.