Jaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 23 hours agoAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comexternal-linkmessage-square125fedilinkarrow-up1653arrow-down114cross-posted to: technology@lemmy.ml
arrow-up1639arrow-down1external-linkAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comJaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 23 hours agomessage-square125fedilinkcross-posted to: technology@lemmy.ml
minus-squareAffidavit@lemmy.worldlinkfedilinkEnglisharrow-up11arrow-down6·9 hours ago“…for multi-step tasks”
minus-squareloonsun@sh.itjust.workslinkfedilinkEnglisharrow-up4·31 minutes agoIt’s about Agents, which implies multi step as those are meant to execute a series of tasks opposed to studies looking at base LLM model performance.
“…for multi-step tasks”
It’s about Agents, which implies multi step as those are meant to execute a series of tasks opposed to studies looking at base LLM model performance.