Jaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 1 day agoAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comexternal-linkmessage-square143fedilinkarrow-up1689arrow-down116cross-posted to: technology@beehaw.orgtechnology@lemmy.ml
arrow-up1673arrow-down1external-linkAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comJaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 1 day agomessage-square143fedilinkcross-posted to: technology@beehaw.orgtechnology@lemmy.ml
minus-squarePunkie@lemmy.worldlinkfedilinkEnglisharrow-up2arrow-down3·22 hours agoI’d compare LLMs to a junior executive. Probably gets the basic stuff right, but check and verify for anything important or complicated. Break tasks down into easier steps.
minus-squarezbyte64@awful.systemslinkfedilinkEnglisharrow-up1·edit-21 hour agoA junior developer actually learns from doing the job, an LLM only learns when they update the training corpus and develop an updated model.
I’d compare LLMs to a junior executive. Probably gets the basic stuff right, but check and verify for anything important or complicated. Break tasks down into easier steps.
A junior developer actually learns from doing the job, an LLM only learns when they update the training corpus and develop an updated model.