Post

One of the many joys of using AI for programming is the creation of huge PRs on complex topics that the authors barely understand, but still suggest "because they work". Here's a great example from #OCaml github.com/ocaml/ocaml/... Kudos to OCaml's maintainers for handling this so gracefully.

The committer 'keeping AI on the straight and narrow' somehow resulted in headers crediting someone else. Pretty funny.

What a colossal waste of time for everyone involved. I use LLMs for code generation, too, but if I get a plausible implementation out of it in a day, I expect to take about 4x as long reviewing it, refactoring it, and making it more robust, and then I still don't entirely trust it.

I totally get it. I also use LLMs from time to time, but I'd never commit something or file a PR unless I understand fully the code there. From me the LLM-generated code is just a starting point. Working code is often not the same as good/clear/maintainable/performant/secure/robust code.

This doesn’t seem like much of a timesaver. Personally, I’ve committed to just writing the code, even if it’s frustrating or boring. Doing the work myself is much more likely to improve my skills and lead to insights that save me time and energy in the future.