☆ Yσɠƚԋσʂ ☆@lemmy.ml to Programmer Humor@lemmy.mlEnglish · 2 days agoWe're cooked y'all 🤣lemmy.mlimagemessage-square41fedilinkarrow-up1158arrow-down11 cross-posted to: programmer_humor@programming.dev
arrow-up1157arrow-down1imageWe're cooked y'all 🤣lemmy.ml☆ Yσɠƚԋσʂ ☆@lemmy.ml to Programmer Humor@lemmy.mlEnglish · 2 days agomessage-square41fedilink cross-posted to: programmer_humor@programming.dev
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up2·2 days agoI expect you could probably do a lot better with a model trained on a specific language, and it could probably be much smaller than a general model as well.
minus-squareroux [he/him, they/them]@hexbear.netlinkfedilinkEnglisharrow-up1·1 day agoNow that I think of it, I wonder if the Astro team has AI shit built into their VSCode plugin.
minus-square☆ Yσɠƚԋσʂ ☆@lemmy.mlOPlinkfedilinkarrow-up2·1 day agoThat would make for a pretty heavy plugin, it still takes sizable resources to run even smaller models locally.
I expect you could probably do a lot better with a model trained on a specific language, and it could probably be much smaller than a general model as well.
Now that I think of it, I wonder if the Astro team has AI shit built into their VSCode plugin.
That would make for a pretty heavy plugin, it still takes sizable resources to run even smaller models locally.