Chris Remington@beehaw.orgM to Technology@beehaw.org · 1 day agoOpenAI finds evidence other AI agents escaped containment as it widens hacking probewww.reuters.comexternal-linkmessage-square4fedilinkarrow-up15
arrow-up15external-linkOpenAI finds evidence other AI agents escaped containment as it widens hacking probewww.reuters.comChris Remington@beehaw.orgM to Technology@beehaw.org · 1 day agomessage-square4fedilink
minus-squarePowderhorn@beehaw.orglinkfedilinkEnglisharrow-up14·1 day agoI have a hard time equating “the LLM did what we told it” with “hacking.” But hey, let’s throw “escaped containment” in just to make it Serious™.
I have a hard time equating “the LLM did what we told it” with “hacking.” But hey, let’s throw “escaped containment” in just to make it Serious™.