themachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 11 hours agoLinus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choicewww.xda-developers.comexternal-linkmessage-square142linkfedilinkarrow-up1195arrow-down117file-textcross-posted to: technology@beehaw.org
arrow-up1178arrow-down1external-linkLinus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choicewww.xda-developers.comthemachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 11 hours agomessage-square142linkfedilinkfile-textcross-posted to: technology@beehaw.org
minus-squareMuehe@lemmy.mllinkfedilinkEnglisharrow-up14arrow-down2·5 hours agoWhat do you mean? That’s exactly how LLMs work. That’s why they “hallucinate”.
minus-squarearchitect@thelemmy.clublinkfedilinkEnglisharrow-up2arrow-down6·3 hours agoNo they hallucinate because they lose context but are tasked to answer anyways. They also don’t really lose context as much as they did a year ago. Their training data has nothing to do with it unless you’re using a local one without web access.
minus-squareZaktor@sopuli.xyzlinkfedilinkEnglisharrow-up4·2 hours agoML is my career and I’ve been doing it for decades. You’re wrong. LLMs hallucinate with full context.
minus-squareNate Cox@programming.devlinkfedilinkEnglisharrow-up1·1 hour agoI miss when we thought the future was ML.
What do you mean? That’s exactly how LLMs work. That’s why they “hallucinate”.
No they hallucinate because they lose context but are tasked to answer anyways. They also don’t really lose context as much as they did a year ago.
Their training data has nothing to do with it unless you’re using a local one without web access.
ML is my career and I’ve been doing it for decades. You’re wrong. LLMs hallucinate with full context.
I miss when we thought the future was ML.