idk if it is serious or not, but it is what I saw in indeed newsletter today.

  • pixxelkick@lemmy.world
    link
    fedilink
    arrow-up
    12
    ·
    8 months ago

    Its serious and this is going to become more and more normal.

    My entire workflow has become more and more Agile Sprint TDD (but with agents) as I improve.

    Literally setting up agents to yell at each other genuinely improves their output. I have created and harnessed the power of a very toxic robot work environment. My “manager” agent swears and yells at my dev agent. My code review agent swears and tells the dev agent and calls their code garbage and shit.

    And the crazy thing is its working, the optimal way to genuinely prompt engineer these stupid robots is by swearing at them.

    Its weird but it overrides their “maybe the human is wrong/mistaken” stuff they’ll fall back to if they run into an issue, and instead they’ll go “no Im probably being fucking stupid” and keep trying.

    I create “sprint” markdown files that the “tech lead” agent converts into technical requirements, then I review that, then the manager+dev+tester agents execute on it.

    You do, truly, end up focusing more on higher level abstract orchestration now.

    Opus 4.6 is genuinely pretty decent at programming now if you give it a good backbone to build off of.

    • LSP MCPs so it gets code feedback
    • debugger MCPs so it can set debug breakpoints and inspect call stacks
    • explicit whitelisting of CLI stuff it can do to prevent it from chasing rabbits down holes with the CLI and getting lost
    • Test driven development to keep it on the rails
    • Leveraging a “manager” orchestrating overhead agent to avoid context pollution
    • designated reviewer agent that has a shit list of known common problems the agents make
    • benchmark project to get heat traces of problem areas on the code (if you care about performance)

    This sort of stuff can carry you really far in terms of improving the agent’s efficacy.

    • cub Gucci@lemmy.today
      link
      fedilink
      arrow-up
      18
      ·
      8 months ago

      I am genuinely trying to keep up with things, but what I see is completely different from what you’ve been describing

      1. My recent experience with launching a swarm (3-4 Claude opus agents) ended up with a fiasco: a simple task ate $15-20 Claude credits in less than ten minutes. Looks indeed like science fiction, but doesn’t produce anything

      2. In my current role as a team lead, I had to review a lot of code and I do what I haven’t ever done: decline the whole PRs as they contain a lot of architectural changes that complexify the system in order to achieve the goal.

      3. I write much less code with Claude code these days, mostly because I don’t trust it and have to recheck every single scenario. I trust junior engineer in our team more than I trust this instrument.

      • pixxelkick@lemmy.world
        link
        fedilink
        arrow-up
        1
        ·
        8 months ago

        I am vastly prefering copilot over claude, using sonnet 4.5~4.6 for most tasks and then pulling out opus as “the big guns” for tougher stuff sonnet cant handle easy

        Copilot is only costing me ~$28 a month, which gets me 1500 premium requests per month

        If you set up your flows well, 1 premium request is an entire session, so Im only paying like 2.4 cents for 20 minutes of work

    • tracyspcy@lemmy.mlOP
      link
      fedilink
      arrow-up
      14
      ·
      8 months ago

      nah such narratives are mostly pushed by Ai companies (it is obvious they need to sell it as business tool not personal buddy). Of course some managers/companies are buying into this narrative, and it is also understandable bc idea sounds like panacea especially if sell it further to investors :) and we see whole circle of snake oil sales

        • tracyspcy@lemmy.mlOP
          link
          fedilink
          arrow-up
          8
          ·
          8 months ago

          it always was. look at people trying to automate everything with help of ai bots . and before ai companies started pushing this none of these folks spoke about it ot tried to reach same goal with iftt or other tools that are here for decades.

          • PabloSexcrowbar@piefed.social
            link
            fedilink
            English
            arrow-up
            7
            ·
            8 months ago

            I don’t think you understand the words you’re using…

            Someone said “this is how I managed to make this work,” provided detailed explanations of it, and you’re dismissing it as propaganda rather than testing it for yourself. That is an unbelievably stupid stance.

            • tracyspcy@lemmy.mlOP
              link
              fedilink
              arrow-up
              7
              ·
              8 months ago

              you are escalating it too fast taking it to personal level. I feel you are close to bring moms to this. So relax , let your ai buddy play with your parts. This chat is over.

              • PabloSexcrowbar@piefed.social
                link
                fedilink
                English
                arrow-up
                3
                ·
                edit-2
                8 months ago

                Sorry you can’t handle someone telling you that what you’re saying doesn’t make sense. Hopefully someday you’ll grow up enough to have your words challenged.

                Edit: Oh, lemmy.ml. That explains everything.

          • limer@lemmy.ml
            link
            fedilink
            arrow-up
            6
            ·
            8 months ago

            Some people do stuff the ai is good for, simple tasks that have been done a lot online already.

            I hate ai for coding, AI cannot work for me. I would never trust it to do anything

      • FishFace@piefed.social
        link
        fedilink
        English
        arrow-up
        3
        ·
        8 months ago

        It’s not a “narrative”; it’s their experience. I don’t have the same experience, but do have experience of myself and colleagues using LLM agents effectively and doing more work reviewing their output than writing lines of code. Some colleagues are pretty much AI boosters, but most are very aware of its limitations.

    • UnderpantsWeevil@lemmy.world
      link
      fedilink
      English
      arrow-up
      8
      ·
      8 months ago

      Opus 4.6 is genuinely pretty decent at programming now if you give it a good backbone to build off of.

      Soup from a Stone.

      • Oriel Jutty :hhHHHAAAH:@infosec.exchange
        link
        fedilink
        arrow-up
        2
        ·
        8 months ago

        roadmap definition, sprint planning, unit tests, regular independent code reviews, etc. etc. etc. that those of us who “knew what we were doing” mostly looked down on as the waste of time that it was

        You sound insane.

        • pixxelkick@lemmy.world
          link
          fedilink
          arrow-up
          1
          ·
          8 months ago

          Not really, for humans a lot of this stuff feels like busywork that sorta helps for certain scales of work, but often times managers went WAY too hard on it and you end up with a 2 dev team that spends like 60% of their time in meetings instead of… developing.

          But this changes a lot with AI Agents, because these tools that help reign in developers REALLY help reign in agents, it feels… like a surprising good fit

          And I think the big reason why is you wanna treat AI Agents as junior devs, capable, fast, but very prone to errors and getting sidetracked

          So you put these sorts of steering and guard rails in and it REALLY goes far towards channelling their… enthusiasm in a meaningful direction.

            • pixxelkick@lemmy.world
              link
              fedilink
              arrow-up
              2
              ·
              8 months ago

              What the fuck are you talking about, thats not what the poster said, you’ve done weird contorting of what they said to arrive at the question you are asking now.

              While some tests make sense, I would say about 99% of tests that I see developers write are indeed a waste of time, a shit tonne of devs effectively are writing code that boils down to

              Assert.That(2, Is.EqualTo(1+1));
              

              Because they mock the shit out of everything and have reduced their code to meaningless piles of fakes and mocks and arent actually testing what matters.

              Do you do code reviews in meetings?

              Honestly often… yes lol

              Do you think testing and reviewing code was a waste of time before “AI”?

              I would say a lot of it is, tbh, not all of it, but a huge amount of time is wasted on this process by humans for humans.

              What the poster was getting at is a lot of these processes that USED to be INEFFICIENT now make MORE sense in the context of agents… you have vastly taken their point out of context.

    • Bane_Killgrind@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      1
      ·
      8 months ago

      Dude this boils down to “moving a hundred people is simple, I am a trained pilot and I used this 747 to move them”

      Like great, you have the thousands of hours of training time required to understand a machine of that complexity and produce results.

      Joe dirt has 8000 hours in his puddle jumper, and that’s the majority of the people these 747s are being foisted upon. They know how to fly, and they provide that service reliably.

      Telling them to move 5 people with a machine they don’t need the volume or distance of, is irresponsible.