Chris Remington@beehaw.orgM to Technology@beehaw.org · 26 days agoOpenAI finds evidence other AI agents escaped containment as it widens hacking probewww.reuters.comexternal-linkmessage-square4linkfedilinkarrow-up15arrow-down19
arrow-up1-4arrow-down1external-linkOpenAI finds evidence other AI agents escaped containment as it widens hacking probewww.reuters.comChris Remington@beehaw.orgM to Technology@beehaw.org · 26 days agomessage-square4linkfedilink
minus-squarePowderhorn@beehaw.orglinkfedilinkEnglisharrow-up14·26 days 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™.