![](https://lemmy.world/pictrs/image/b0448199-2503-445e-a459-65a5318fef97.jpeg)
![](https://lemmy.ml/pictrs/image/q98XK4sKtw.png)
LLMs are little more than overclocked autocompletes. There’s no actual thinking going on, and they will happily hallucinate outright wrong or dangerous responses to innocuous questions.
I’ve had friends find this out the hard way when they asked ChatGPT to write them C for a class, only to get their faces eaten by UB.
Not a Nix user, but IIRC
nixpkgs
is actually bigger than the AUR by a long shot.