sanitation@lemmy.radio to Technology@lemmy.worldEnglish · 2 days agoResearchers gaslit Claude into giving instructions to build explosiveswww.theverge.comexternal-linkmessage-square24linkfedilinkarrow-up1209arrow-down18
arrow-up1201arrow-down1external-linkResearchers gaslit Claude into giving instructions to build explosiveswww.theverge.comsanitation@lemmy.radio to Technology@lemmy.worldEnglish · 2 days agomessage-square24linkfedilink
minus-squareBodilessGaze@sh.itjust.workslinkfedilinkEnglisharrow-up1·21 hours agoInterestingly, LLMs are horrible at Zork: https://arxiv.org/abs/2602.15867 Our results reveal that all tested models achieve less than 10% completion on average, with even the best-performing model (Claude Opus 4.5) reaching only approximately 75 out of 350 possible points
Interestingly, LLMs are horrible at Zork: https://arxiv.org/abs/2602.15867