25 comments

  • ks2048 14 minutes ago

    No doubt fuzzers (vibecoded or otherwise) can be powerful, but can't you just mark all "/" as potential divide by zero errors?

    I guess sometimes developers think they "know" some variable won't be zero, but unless it checked explicitly or by the compiler, that shouldn't be trusted.

      dooglius 5 minutes ago

      What are you suggesting and how would it be different than how SIGFPE already works?

      wvbdmp 8 minutes ago

      I mean there could be a guard clause? But yeah, seems like this could be statically evaluated like how some IDEs see a null check and don’t complain about nullability within the same scope.

  • akshay_akula 23 minutes ago

    The open ended bug hunt is the best use case for these agents. Finding nothing costs a few dollars, finding a division by zero in ffmpeg pays for itself.

  • dabinat an hour ago

    It’s interesting how AI may both raise and lower the quality of software. It’s very easy to send an AI agent on an open-ended bug hunt, and if it wastes a bunch of time and effort and finds nothing, no big deal. Time is much more important for a human developer with a salary.

      dmix an hour ago

      Finding the bugs with LLMs is easy. Reviewing the output, cleaning it up, and making sure it doesn't break something else is the hard part.

        bewareofscams 41 minutes ago

        No, you frame it wrong. It's not reviewing output, it's (at the very least in this particular case) reviewing the outcome, - and without LLMs you ain't getting to review anything.

        This ship has sailed, LLMs do find bugs, do save time, and do tasks dweebs considered art or craft (unable to do real either) with flying colors.

          shevy-java 38 minutes ago

          > LLMs do find bugs, do save time

          They find bugs but whether they save time is nowhere near as clear as you try to insinuate here.

            pixl97 37 minutes ago

            They save time in finding bugs.

              lukan 35 minutes ago

              And for me they also save time in fixing bugs.

      evenhash 21 minutes ago

      > It’s very easy to send an AI agent on an open-ended bug hunt, and if it wastes a bunch of time and effort and finds nothing, no big deal.

      No big deal? It’s not like it’s free… tokens cost money.

      Supermancho an hour ago

      I don't care if you call it an over-engineered looping machine or what, there are concrete benefits to using LLMs for this. They work faster than developing your own looping algorithm and more often produce useful results than not.

      eviks an hour ago

      But what's your expectation of the net?

      shevy-java 39 minutes ago

      I dislike AI, but if AI finds real bugs then this is in my opinion objectively a positive thing. Of course the question is what constitutes a real bug.

        pixl97 36 minutes ago

        Unfiltered models will help build exploits for the bugs they find, so there is some means of measuring their efficacy.

  • 12j3afAv an hour ago

    Generating an incorrect input file seems to be the easiest task of all for any fuzzer.

    Generating correct input to get deep into the call stack and then finding something is the hard part.

  • Surac an hour ago

    send patches

      rs_rs_rs_rs_rs 20 minutes ago

      ...they did.

        ligarota 9 minutes ago

        Where?

        They only suggested a basic guard, chich can be useless if this case never happens

  • VCFundedGenYer an hour ago

    The fruits of using LLMs to code. You'll waste far more time finding what it quietly and subtly wrecked than you would have if you just coded it yourself.

      jaggederest an hour ago

      Those sneaky LLMs going 7 years into the past and committing as a human:

      https://code.ffmpeg.org/FFmpeg/FFmpeg/commit/8eda3c7f91e1a5b...

        wiseowise 14 minutes ago

        It’s obviously Claude 69 with time travel functionality, that’s too dangerous to release to public. They’re working on space-time limiting sandbox to prevent these issues.

      vegnus an hour ago

      You're not reading it right. The bug was found using a vibecoded fuzzer.

        12j3afAv 43 minutes ago

        I wonder from where Claude stole this fuzzer.

          pjankiewicz 16 minutes ago

          Or it used something called an "analogy" which is a valid way to solve new problems.