themachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 16 days agoLinus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choicewww.xda-developers.comexternal-linkmessage-square293linkfedilinkarrow-up1183arrow-down120file-textcross-posted to: linux@programming.devtechnology@lemmy.ziptechnology@beehaw.org
arrow-up1163arrow-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 · 16 days agomessage-square293linkfedilinkfile-textcross-posted to: linux@programming.devtechnology@lemmy.ziptechnology@beehaw.org
minus-squareMuehe@lemmy.mllinkfedilinkEnglisharrow-up10arrow-down1·16 days agoWhat do you mean? That’s exactly how LLMs work. That’s why they “hallucinate”.
minus-squarearchitect@thelemmy.clublinkfedilinkEnglisharrow-up2arrow-down1·edit-216 days 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.
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.