Sahwa@reddthat.com to Technology@lemmy.worldEnglish · 3 hours agoMicrosoft says Copilot will 'finish your code before you finish your coffee' adding fuel to the Windows 11 AI controversy that's still ragingwww.techradar.comexternal-linkmessage-square18fedilinkarrow-up175arrow-down15
arrow-up170arrow-down1external-linkMicrosoft says Copilot will 'finish your code before you finish your coffee' adding fuel to the Windows 11 AI controversy that's still ragingwww.techradar.comSahwa@reddthat.com to Technology@lemmy.worldEnglish · 3 hours agomessage-square18fedilink
minus-squareMadMadBunny@lemmy.calinkfedilinkEnglisharrow-up9·edit-22 hours agoBut, will it work, huh? HUH? I can also type a bunch of random sentences of words. Doesn’t make it more understandable.
minus-squareryannathans@aussie.zonelinkfedilinkEnglisharrow-up5arrow-down4·2 hours agoSome models are getting so good they can patch user reported software defects following test driven development with minimal or no changes required in review. Specifically Claude Sonnet and Gemini So the claims are at least legit in some cases
minus-square6nk06@sh.itjust.workslinkfedilinkEnglisharrow-up6·1 hour agoOh good. They can show us how it’s done by patching open-source projects for example. Right? That way we will see that they are not full of shit. Where are the patches? They have trained on millions of open-source projects after all. It should be easy. Show us.
minus-squareTrigger2_2000@sh.itjust.workslinkfedilinkEnglisharrow-up8·2 hours agoWill it execute . . . probably. Will it execute what you want it to . . . probably not.
But, will it work, huh? HUH?
I can also type a bunch of random sentences of words. Doesn’t make it more understandable.
Some models are getting so good they can patch user reported software defects following test driven development with minimal or no changes required in review. Specifically Claude Sonnet and Gemini
So the claims are at least legit in some cases
Oh good. They can show us how it’s done by patching open-source projects for example. Right? That way we will see that they are not full of shit.
Where are the patches? They have trained on millions of open-source projects after all. It should be easy. Show us.
Will it execute . . . probably.
Will it execute what you want it to . . . probably not.