Thread

1. jabedude · 1790975528 · focus · HN ↗

   How is Zig doing as a project? I remember they took a hard line against AI

   1. abc42 · 1790975852 · focus · HN ↗

      It looks like they're spending 5 months what should be a 1 month job these days.

      1. onlyrealcuzzo · 1790975988 · focus · HN ↗

         Filed a compiler bug related to dwarf tables that screws up debugging and line of code coverage that they completely ignored, just because I mentioned that I had every LLM check it to confirm it's a bug, since all I know is what kcov and every coverage tool generates incorrect coverage data for my repo, for 100% certain.

         1. bendmorris · 1790976655 · focus · HN ↗

            Sounds like you violated the clearly stated project rules and admitted to it. Are you surprised that they're not engaging with you?

            1. IshKebab · 1790976979 · focus · HN ↗

               Wow I thought surely they wouldn't object to using AI to confirm bugs, but they really do.

               Tbf I guess as a popular open source project not using AI to fix bugs, they probably already have more open bugs than they can ever fix so it doesn't really help them for people to find more.

               I would imagine his bug was actually ignored just because Zig has 2700 open bugs, rather than some AI policy violation.

               1. audunw · 1790978042 · focus · HN ↗

                  They don’t, at least not any more. Andrew Kelley has explicitly stated that he sees the value of using LLMs to uncover bugs. Inspired by sqllite project.

                  <a href="https:&#x2F;&#x2F;youtu.be&#x2F;zwi5b5xSsKA?is=PTjJJjSnVMdRuZag" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;zwi5b5xSsKA?is=PTjJJjSnVMdRuZag

                  They may just be taking the slow route of rejecting by default until they can be sure that the usage of LLMs provides long term value. I don’t see anything wrong with that. If you’re writing robust software, using LLMs at this stage is a bit of a gamble. We don’t fully know the long term effects on code quality yet.

                  1. saghm · 1790978855 · focus · HN ↗

                     Ah, so yet another language in the long line of &quot;I&#x27;m smart enough to use this but you the user are not&quot;

                     1. unleaded · 1790979223 · focus · HN ↗

                        Project maintainers know what level of AI use is acceptable for themselves, and quantifying it and enforcing it for random contributors is very difficult.
                     2. Capricorn2481 · 1790983366 · focus · HN ↗

                        This is because they got so many shit admissions from people using LLMs they were wasting time reviewing them.
                  2. csande17 · 1790991200 · focus · HN ↗

                     He sees the value of using LLMs... only after performing NASA-level verification and fully comprehensive fuzzing using traditional tools. Since Zig has not done those things, LLM-generated bugs are still banned.

Unofficial Hacker News client; not affiliated with Y Combinator.