@dragnucs@lemmy.ml
member since 15 Sep 2021 00:43
comments
- on Engineer says Claude Code has made his job "soul-sucking" as workers spend 12-hour days pressing enter in c/technology@beehaw.org · 1d ago
-
on Engineer says Claude Code has made his job "soul-sucking" as workers spend 12-hour days pressing enter in c/technology@beehaw.org · 1d ago
He could have configured it to auto approve.
-
on FOSS and Artificial Intelligence in c/foss@beehaw.org · 13 Sep 2026
Still, 7500 MAD (USD 760) is not cheap at all, and you still need the rest of the computer to put it in. So maybe 1400 USD as still not able to do complicated stuff.
And the 5090? our of question: jawa.gg/…/msi-geforce-rtx-5090-32g-ventus-3x-oc
-
on FOSS and Artificial Intelligence in c/foss@beehaw.org · 13 Sep 2026
It is very expensive to self host your AI/LLM and have it function locally. You sure can self host it and get it to work correctly but it too slow or too inaccurate for anything useful. Maybe some new model can be made to run on comoddity hardware or that new cheap hardware can be made to run AI decently, but as of now, on all the equipment I have, I cannot get it to a usable state. You can watch videos on internet on what it takes to get it to run and still have mediocre results.
In the enterprise you could link jira tickets to github copilite on the cloud and it makes and merges and deploys PRs for you.