themachinestops@lemmy.dbzer0.com to Technology@lemmy.worldEnglish · 12 hours agoLinus Torvalds used AI to fix a Linux bug, and now LLM critics on Linux face an uncomfortable choicewww.xda-developers.comexternal-linkmessage-square132linkfedilinkarrow-up10arrow-down10file-textcross-posted to: [email protected]
arrow-up10arrow-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 · 12 hours agomessage-square132linkfedilinkfile-textcross-posted to: [email protected]
minus-squareshirasho@feddit.onlinelinkfedilinkEnglisharrow-up0·3 hours agoLLMs suck at writing code, but they are absolutely amazing at reading code and finding bugs. I am firmly against the usage of LLMs to write anything, but they have a place as a diagnostics tool when verified by a human.
minus-squarerothaine@lemmy.ziplinkfedilinkEnglisharrow-up0·42 minutes agoOpus-class and higher models are actually great at writing code, but maybe it’s language dependent? I primarily work in TypeScript.
minus-squaredatavoid@sh.itjust.workslinkfedilinkEnglisharrow-up0·2 hours agoLine completion is pretty damn handy, it’s when you start asking for whole functions that things go downhill
LLMs suck at writing code, but they are absolutely amazing at reading code and finding bugs. I am firmly against the usage of LLMs to write anything, but they have a place as a diagnostics tool when verified by a human.
Opus-class and higher models are actually great at writing code, but maybe it’s language dependent? I primarily work in TypeScript.
Line completion is pretty damn handy, it’s when you start asking for whole functions that things go downhill