Jaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 1 day agoAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comexternal-linkmessage-square154fedilinkarrow-up1707arrow-down114cross-posted to: technology@beehaw.org
arrow-up1693arrow-down1external-linkAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comJaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 1 day agomessage-square154fedilinkcross-posted to: technology@beehaw.org
minus-squareAffidavit@lemmy.worldlinkfedilinkEnglisharrow-up11arrow-down7·12 hours ago“…for multi-step tasks”
minus-squareloonsun@sh.itjust.workslinkfedilinkEnglisharrow-up4·3 hours 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.