Jaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 1 day agoAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comexternal-linkmessage-square51fedilinkarrow-up1519arrow-down113
arrow-up1506arrow-down1external-linkAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comJaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 1 day agomessage-square51fedilink
minus-squareAffidavit@lemmy.worldlinkfedilinkEnglisharrow-up9arrow-down6·11 hours ago“…for multi-step tasks”
minus-squareloonsun@sh.itjust.workslinkfedilinkEnglisharrow-up3·2 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.