← Back to context

Comment by whilenot-dev

2 days ago

> Why would you be unwilling to merge AI code at all?

Are you leaving the third-party aspect out of your question on purpose?

Not GP but for me, it pretty much boils down to the comment from Mason[0]: "If I wanted an LLM to generate [...] unreviewed code [...], I could do it myself."

To put it bluntly, everybody can generate code via LLMs and writing code isn't what defines the dominant work of an existing project anymore, as the write/verify-balance shifts to become verify-heavy. Who's better equipped to verify generated code than the maintainers themselves?

Instead of prompting LLMs for a feature, one could request the desired feature from the maintainers in the issue tracker and let them decide whether they want to generate the code via LLMs or not, discuss strategies etc. Whether the maintainers will use their time for reviews should remain their choice, and their choice only - anyone besides the maintainers should have no say in this.

There's also the cultural problem where the review efforts are non-/underrepresented in any contemporary VCS, and the amount of merged code grants for a higher authority over a repository than any time spent doing reviews or verification (the Linux kernel might be an exception here?). We might need to rethink that approach moving forward.

[0]: https://discourse.julialang.org/t/ai-generated-enhancements-...

11 comments

whilenot-dev

Reply
wagerlabs  2 days ago

I'm strictly talking about the 10-line Zig PR above.

Well-documented and tested.

  • whilenot-dev  2 days ago

    That's certainly a way to avoid questions... I mean sure, but everybody else is talking about how your humongous PRs are a burden to review.

  • globnomulous  1 day ago

    It's worth asking yourself something: people have written substantial responses to your questions in this thread. Here you answered four paragraphs with two fucking lines referencing and repeating what you've already said. How do you expect someone to react? How can you expect anybody to take seriously anything you say, write, or commit when you obviously have so little ability, or willingness, to engage with others in a manner that shows respect and thought?

    I really, truly don't understand. This isn't just about manners, mores, or self-reflection. The inability or unwillingness to think about your behavior or its likely reception are stupefying.

    You need to stop 'contribiting' to public projects and stop talking to people in forums until you figure this stuff out.

    • edstarch  1 day ago

      >I really, truly don't understand. This isn't just about manners, mores, or self-reflection. The inability or unwillingness to think about your behavior or its likely reception are stupefying.

      Shower thought: what does a typical conversation with an LLM look like? You ask it a question, or you give a command. The model spends some time writing a large wall of text, or performing some large amount of work, probably asks some follow up questions. Most of the output is repetitive slop so the user scans for the direct answer to the question, or checks if the tests work, promptly ignores the follow-ups and proceeds to the next task.

      Then the user goes to an online forum and carries on behaving the same way: all posts are instrumental, all of the replies are just directing, shepherding, shaping and cajoling the other users to his desired end (giving him recognition and a job).

      I'm probably reading too much into this one dude but perhaps daily interaction with LLMs also changes how one interacts with other text based entities in their lives.

      3 replies →