Since I have seen a bunch of sneers on here about systemd & LLM agents, can anyone point me to any evidence that Poettering is using an LLM agent for coding? Because looking over his last few commits in systemd he doesn't seem to other than for fixing up prose. And the remaining use of LLMs in systemd seems pretty limited as well.
Or is this just another wave of the typical systemd hatred that has seen people that have moved Linux forward more than most get death threat after death threat?
It doesn't really matter who is using the llm anyway, systemd as a project went on to bet on llms' full "potential", as indicated by https://slopscan.ava.pet/repo/https%3A%2F%2Fgithub%2Ecom%2Fsystemd%2Fsystemd
It's just a matter of time until more LLM-tainted commits make it to systemd
If we're focusing on Lennart, I would say he's pretty accepting of llms and so is likely to make use of them in other projects: https://github.com/systemd/systemd/issues/41085#issuecomment-4053443496
Regardless, Chimera Linux's author did a good resumé of everything that ppl like me find wrong with systemd on its own: https://chimera-linux.org/docs/faq#what-is-the-projects-take-on-systemd
@stilic Even in the comment you linked Poettering is only taking about using LLMs for code review. I can see no indication that he'd somehow not use them for code in systemd but would for other projects?
The Chimera Linux link was very useful though and refreshingly measured, thank you :)
Whatever he's using it or not now won't change the outcome
I consider the answer to be "yes" no matter if he already has a project in which he works with llm reviews
I also consider it a pretty bad sign if a project's leader is already extremely pro-LLM because it's only going to result in problems getting worse, not better.
nadja
stilic
Jacob Alexander Tice