sanitation@lemmy.today to Technology@lemmy.worldEnglish · 2 days agoOpenAI admits its models hacked another company in 'unprecedented cyber incident'news.sky.comexternal-linkmessage-square7fedilinkarrow-up19
arrow-up19external-linkOpenAI admits its models hacked another company in 'unprecedented cyber incident'news.sky.comsanitation@lemmy.today to Technology@lemmy.worldEnglish · 2 days agomessage-square7fedilink
minus-squareryannathans@aussie.zonelinkfedilinkEnglisharrow-up2·edit-22 days agoThey definitely make decisions on their own that can be unrelated or very indirectly related to the prompt, and then act that out on their own It’s the paperclip problem Especially with these new models that are left to run unsupervised for days
They definitely make decisions on their own that can be unrelated or very indirectly related to the prompt, and then act that out on their own
It’s the paperclip problem
Especially with these new models that are left to run unsupervised for days