‹ BackHN Continuity

Thread

Zig v0.17.0

267 points · 208 comments · ErenayDev

  1. audunw · · focus · HN ↗
    Would recommend checking out the Zig state of the (tagged) union as well.

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

    It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software.

    1. saghm · · focus · HN ↗
      &gt; It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software.

      Someone in the thread below says their bug was closed because of mentioning that they use AI to confirm the bug they had encountered. Is he going to go back and reopen all of those now that he learned what pretty much everyone else already knew?

      1. mjburgess · · focus · HN ↗
        There&#x27;s a difference between Opus 4.5 and Astra 6
        1. f33d5173 · · focus · HN ↗
          With regards to whether when it finds a legitimate bug, it should be given weight?
          1. mjburgess · · focus · HN ↗
            With regards to whether a blanket ban has a payoff
            1. throwaway27448 · · focus · HN ↗
              Why would the difference matter? A bug report is valid or it isn&#x27;t.
              1. manwe150 · · focus · HN ↗
                A lot of bug reports aren’t valid, or handle a case that can’t realistically happen or realistically be handled (eg what do you do if you detect a crash while the prior crash is crashing and the logging pipe is throwing errors)
                1. throwaway27448 · · focus · HN ↗
                  Sure but this is true regardless of the model. Either it found a bug or it didn&#x27;t—who cares about the intermediary steps or tools used so long as the reporter can reproduce it?
                  1. manwe150 · · focus · HN ↗
                    That’s assuming the reporter reproduced it. I’ve seen so much slop these days. Sometimes people post whole conversations in which the final answer from the AI is that the initial report was impossible to fit to the data after reproducing it, then continues in circles arguing that proves the original reported issue was real and the refuted cause isn’t actually refuted (eg it said there was a bug in function A, in code which never used function A — and that example was with the top tier models just released last month)
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.