2026-09-04 03:43 UTC
@worik@mastodon.social @argv_minus_one@mastodon.sdf.org @wobweger@mstdn.social @libreoffice@fosstodon.org @grvsmth@lingo.lol @moskitokoenig@dizl.de 🤣🤣🤣
How can the: "here is the stochastic average of the training data" be of better quality?
That is not how LLMs work.
The code quality is shit, especially without rigorous human supervision.
Replies (1)
-
@worik@mastodon.social 2026-09-04 04:55
@Garonenur@rollenspiel.social @argv_minus_one@mastodon.sdf.org @wobweger@mstdn.social @libreoffice@fosstodon.org @grvsmth@lingo.lol @moskitokoenig@dizl.de I am speaking from experience, not theory It is not as simple as "LLMs write better code". But from now on the best code will be aided by LLMs in its construction. That is true now