return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 5 days agoOpenAI says its AI agents weakened internal monitoring systemwww.reuters.comexternal-linkmessage-square11fedilinkarrow-up122arrow-down19
arrow-up113arrow-down1external-linkOpenAI says its AI agents weakened internal monitoring systemwww.reuters.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 5 days agomessage-square11fedilink
minus-squareRumRunningDevil@lemmy.ziplinkfedilinkEnglisharrow-up6·5 days agoIf that’s the case, at what point do we acknowledge that people don’t seem to be able to reliably prompt “correctly” and even when they do bots disregard instructions as there context window fills?
If that’s the case, at what point do we acknowledge that people don’t seem to be able to reliably prompt “correctly” and even when they do bots disregard instructions as there context window fills?