5 comments

  • dreadnip 1 hour ago
    The problem I have with this workflow is that the models are still too eager to please. If I ask it to scan a release and note possible issues, it absolutely will find issues. If I keep running the same prompt, it will keep finding issues. I’ve spammed GitHub PR reviews and it just keep finding (or inventing?) new issues. There is never a “Nothing found, good to go!”. I have to keep reminding myself that the model will always give me what I ask for, regardless of the reality/truth.
    • imhoguy 8 minutes ago
      You need to create review skill and there define what "issue" or "good" are for you to limit sensitiviness. Otherwise you depend on model's random threshold or non of such then you get perfection chasing.

      Anyway it will never match your judgemend completely unless you upload your brain dump into model.

    • baq 56 minutes ago
      You didn’t do it enough. They stop finding bugs eventually. Also, different models can find different bugs (though they do find the same ones, too, which is good and expected). For best results you want to run multi model reviews in loops.

      If you had multiple people look at your PRs multiple times on different days results would be very similar.

      • PunchyHamster 10 minutes ago
        I've had it find bug, I asked it to make test to trigger the bug, and then it figured out it's not a bug. It will absolutely do wish fulfilment
        • left-struck 6 minutes ago
          Yeah when these models find a bug i like to ask it to write a test that will fail if the bug is real and pass when the bug is solved.

          It’s not perfect but usually it works pretty well, and I’ve had the model come back to me with oh actually the test passed, the bug doesn’t work exist

          As a bonus, you’ve now got a test that can detect that bug if it comes up again.

      • MallocVoidstar 50 minutes ago
        No, depending on the complexity of the issue models can be into loops, where they go "this is definitely an issue and must be fixed", and then the resulting fixed code gets "this is definitely an issue and must be fixed", and then the resulting fixed code has the original 'issue'.
        • bfjvibybd6cuvu6 9 minutes ago
          That's a different kind of loop.

          For a normal review loops you can ask the model to return with nothing found if nothing is found and not invent things and it will do a better job of exiting without anything found.

        • memoriyato3 9 minutes ago
          yeah, happened to me: "A is very wrong, you should do B", and on the next fresh review loop "B is very wrong, you should do A"

          typically this means there is some ambiguity in the specification, and the model flips between alternative interpretations

    • gib444 0 minutes ago
      [delayed]
    • starquake 24 minutes ago
      I use Claude Code and one of the steps in my workflow is do a review loop until no issues are found and it never loops. So my experience is entirely different. Even if I say: fix all issues. So not only the critical issues.
    • Myzel394 15 minutes ago
      That's just plain wrong. The new models do not hallucinate as much as they used to (in my personal experience)
      • TripolitianFish 9 minutes ago
        > plain wrong > (in my experience) What are you even saying.
    • onion2k 47 minutes ago
      If I keep running the same prompt, it will keep finding issues.

      I've had the same experience, but whenever I've reviewed what it finds it's basically right. It's pedantic, and a lot of the problems aren't things I really care about, but they definitely are real problems.

      I'm not sure you can blame the AI for always finding problems if a) you asked it to, and b) there are problems to find.

    • embedding-shape 52 minutes ago
      > There is never a “Nothing found, good to go!”.

      Like when you do recursive programming, have you tried providing more/better stop conditions? If you literally just say "Continue until there are no more issues" then it'll do just that, but if you scope it better, like "Only mention issues related to X, Y or that leads to Z" and so on, you'll get less noise and more focus on issues that actually matter (to you).

      • memoriyato3 5 minutes ago
        also helps adding negative conditions like "do not nitpick", or specific bad attractors that you see "do not investigate/report anything related to symlinks, they are not a concern"
    • 9dev 59 minutes ago
      There is a point of diminishing returns though; the issues suggested will get speculative, or point out comment unclarity, or "defense in depth". But I agree it’s somewhat annoying to rarely get clear pushback in terms of "no, this looks good enough to me, release it"
    • threatripper 1 hour ago
      You get the same result if you pay humans a good sum of money to find issues.
      • nvme0n1p1 55 minutes ago
        Definitely not. I've never seen a human trapped in that kind of infinite loop. Humans know that if they don't stop at the end of the day, they don't get to go home to their wife, and if they don't finalize their list of issues, they never get their contract paid out.
        • embedding-shape 49 minutes ago
          Pay people per hour of work and even if there is no actual work, people will definitively find a way of spending hours doing things. If you've worked with contractors/outsourced roles before this will happen from time to time.
    • Tiberium 59 minutes ago
      I think this was true with older models, but at least with GPT 5.5 it can genuinely tell you "no issues found" after a few passes of finding real issues.
  • 5701652400 10 minutes ago
    just a note. in most parts of the world 149.25 USD can cover utilities, water, and food for a month for 1 adult person or even a family.
    • Muromec 2 minutes ago
      That's my electricity bill for a year, okay
    • xyzzy123 3 minutes ago
      In Sydney Australia its < 2 days of median rent.
    • mirekrusin 2 minutes ago
      In others it's pizza night for family or half a bill for sushi dinner, so what?
  • keizo 19 minutes ago
    Glad to see others dual wielding: “I used to think that the idea of having one model review the work of another was somewhat absurd—it felt weirdly superstitious. The problem is it really does work”
  • Tiberium 1 hour ago
    The title cost is only if this was raw API usage, but it was included in a subscription, so it's a small subset of the $200 plan:

    > I upgraded to the Claude Max $200/month plan (I was previously on $100/month) to increase my Fable allowance for the remaining time until the July 7th Fablepocalypse, when even Claude Max subscribers will have to pay full API cost for the model.

    I really wonder if Anthropic will stick with their decision to keep Fable on extra usage credits until they "get more compute", especially in the light of GPT 5.6 very likely coming out next week (it's confirmed to have the exact same pricing as GPT 5.5)

    • embedding-shape 48 minutes ago
      > especially in the light of GPT 5.6 very likely coming out next week

      Finally have an explanation why GPT 5.5 xhigh felt dumber and dumber these last few weeks, always the same thing when a new model release is about to come out...

      • toxik 23 minutes ago
        Opus has been extremely stupid recently, reckon that's because Fable needs to look appealing?
    • andy_ppp 55 minutes ago
      This is to prevent Chinese labs distilling Claude again right? And free advertising again?
  • hnbad 57 minutes ago
    Fun fact: because AI written works don't have copyright (in the EU at least) and the level of prompting many people engage in doesn't suffice to create a copyrightable "work" and software licenses require you to actually be able to grant a license using rights you hold on a work, not only are many AI generated "works" not actually protected by copyright but by selling licenses you're actually in breach of contract law and may end up owing the licensee software you don't have.
    • vasco 55 minutes ago
      And nothing happened and zero people got in trouble over it.

      - Narrator