Jaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 10 days agoAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comexternal-linkmessage-square198fedilinkarrow-up1888arrow-down119cross-posted to: technology@beehaw.org
arrow-up1869arrow-down1external-linkAI agents wrong ~70% of time: Carnegie Mellon studywww.theregister.comJaden Norman@lemmy.world to Technology@lemmy.worldEnglish · 10 days agomessage-square198fedilinkcross-posted to: technology@beehaw.org
minus-squarelepinkainen@lemmy.worldlinkfedilinkEnglisharrow-up16arrow-down6·10 days agoWrong 70% doing what? I’ve used LLMs as a Stack Overflow / MSDN replacement for over a year and if they fucked up 7/10 questions I’d stop. Same with code, any free model can easily generate simple scripts and utilities with maybe 10% error rate, definitely not 70%
minus-squareCodeBlooded@programming.devlinkfedilinkEnglisharrow-up6arrow-down5·10 days agoI’m far more efficient with AI tools as a programmer. I love it! 🤷♂️
minus-squareImgonnatrythis@sh.itjust.workslinkfedilinkEnglisharrow-up1·10 days agoDefinitely at image generation. Getting what you want with that is an exercise in patience for sure.
minus-squareTimewornTraveler@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up1·9 days agoit specifies the tasks in the article
Wrong 70% doing what?
I’ve used LLMs as a Stack Overflow / MSDN replacement for over a year and if they fucked up 7/10 questions I’d stop.
Same with code, any free model can easily generate simple scripts and utilities with maybe 10% error rate, definitely not 70%
I’m far more efficient with AI tools as a programmer. I love it! 🤷♂️
Definitely at image generation. Getting what you want with that is an exercise in patience for sure.
it specifies the tasks in the article