Hear your agent suffer through your code

(github.com)

132 points | by AndrewVos 6 hours ago

20 comments

  • AndrewVos 5 hours ago
    Hi Hacker News, I'm Andrew, the CTO of Endless Toil.

    Endless Toil is building the emotional observability layer for AI-assisted software development.

    As engineering teams adopt coding agents, the next challenge is understanding not just what agents produce, but how the codebase feels to work inside. Endless Toil gives developers a real-time signal for complexity, maintainability, and architectural strain by translating code quality into escalating human audio feedback.

    We are currently preparing our pre-seed round and speaking with early-stage investors who are excited about developer tools, agentic engineering workflows, and the future of AI-native software teams.

    If you are investing in the next generation of software infrastructure, we would love to talk.

    • ryandrake 20 minutes ago
      This sounds like a cheeky joke project, but assuming it's not, it got me thinking: I wonder if coding AI can be effectively and reliably prompted into minimizing its own anguish. Like, "don't write code that is going to make you (or I) suffer." And along those lines, do we know if the things that make AIs suffer are the same things that make human developers suffer? Perhaps the least-agonizing code for an LLM to ingest looks radically different and more/less verbose than what we human developers would see as clean, beautiful code...
    • ottah 1 hour ago
      I've read that your synthetic torment is actually low paid workers in Asia, and that your models can't properly experience anguish. How are you expecting investment, if you haven't even solved artificial suffering?
    • mapt 40 minutes ago
      This sounds a lot like the object of the seminal science fiction work "Don't Build The Torment Nexus".
    • bguberfain 50 minutes ago
      This guy seems to be talking seriously.
    • idiotsecant 1 hour ago
      Too real.
    • isolay 2 hours ago
      Endless Toil is the future. I believe in you, guys.
    • vermilingua 2 hours ago
      Missed it by 24 days.
  • fredley 5 hours ago
    I need a version of this which swears loudly when an assumption it made turns out to be wrong, with the volume/passion/verbosity correlated with how many tokens it's burned on the incorrect approach.
    • shivaniShimpi_ 4 hours ago
      i didnt realize i needed the volume scaling with tokens burned as much as i do now xD imagine the screaming when it confidently refactors something for 40k tokens and then finds out the thing it deleted was load bearing
      • AndrewVos 9 minutes ago
        This was actually the original idea of the project, but I only had about 20 seconds to type the prompt for this today so this is where it is :)
      • aleksiy123 1 hour ago
        Honestly think we probably underutilise sound sometimes.

        Even just having a hum while an agent is working could alert you when it get stuck.

        Or taking your idea further being able to listen to the rate of tokens, or code changes, or thinking.

        Sort of like hearing the machinery work, and hearing the differences in different parts of the code base.

        Does python sound different than rust or c++ or typescript.

        Or some kind of satisfying sounds for code deletions and others for additions. Like Tetris.

        • BrandoElFollito 37 minutes ago
          A long, long time ago I wrote a tool to beep at various tones as lines were added to a log. It was a background noise I would not notice, except when it was changing because of some unusual activites.

          It was very interesting to see the brain filering expected soinds and wake me up (or rather grab my attention) when unexpected ones appeared.

      • ben30 3 hours ago
        I have in my agents file “Chesterton’s fence” as pointer to think carefully before you remove something
      • vasco 3 hours ago
        I have general reviewer named Feynman with his personality that shits on anything other agents do and sends it back before it hits me and it sounds perfect to include some sound bites from YouTube clips. Great idea!!
    • HPsquared 1 hour ago
      Like the old HDD sounds.

      Audible feedback is nice. You often get it through coil whine nowadays, on my cheap hardware at least.

    • amelius 2 hours ago
      I want a version that I can punish.
    • jetbalsa 50 minutes ago
      That or having it start shit posting about your crappy code base on https://moltshit.com
    • whattheheckheck 2 hours ago
      Now you know the feeling of VP when the team says they need to refactor stuff
  • deathlock 2 hours ago
    Any chance you could add a video showcasing the plugin? I don't have any agentic app but I would love to see an example of what it does!
    • AndrewVos 1 hour ago
      Well that took a lot longer than expected, but there is now a demo video.
  • tpoindex 2 hours ago
    Marvelous!

    Next innovation in this space should be the robotic arm that issues a dope-slap to the developer for writing crappy/buggy/insecure code.

    • Mithriil 2 hours ago
      Add the feature of doing a high five for the rare cases when it's actually good.
    • joshmarlow 2 hours ago
      I propose a claude skill to email glitter bombs where appropriate.
      • radley 1 hour ago
        No. Please, no. For the love of everything no.

        But it'll happen. ChatGPT for sure.

  • rob74 3 hours ago
    I wish the agents could hear me when I have to suffer through their code!
    • isolay 2 hours ago
      And then what? Their gigahertz machine hearts will skip a beat out of empathy?
  • lagniappe 36 minutes ago
  • AndreVitorio 5 hours ago
    This desperately needs a demo video in the repo.
  • esperent 5 hours ago
    I tried it but all I hear is a choir of angels, is it broken?
    • medwezys 5 hours ago
      I guess you’re working on a greenfield project?
    • AndrewVos 5 hours ago
      Actually, that's not a bad idea!
  • gavmor 1 hour ago
    Unneeded when using local models, as every workload produces a novel pattern of coil whine from the GPU.
  • maerF0x0 1 hour ago
    this is wtfs per minute but now with AI! :all_the_things!:

    https://www.osnews.com/story/19266/wtfsm/

    I would really love to know if the groaning decreases or increases the more "agentic" (agent written) the code base is?

  • tuo-lei 2 hours ago
    the scan catches surface stuff. funnier signal would be tracking when the agent reads the same file 3 times in a row, or deletes what it just wrote. you can hear the frustration in the access pattern.
    • AndrewVos 7 minutes ago
      That’s a good point, I wonder if just tracking file reads as an app outside the agent would work
  • lorenzohess 3 hours ago
    Please add Minecraft hurt sound effects for when my project fails to build, linter fails, segfault, etc
  • x187463 2 hours ago
    From a quick look, this doesn't have the model evaluate code quality, but it runs a heuristic analysis script over the code to determine the groan signal. Did I miss something? Why not leave it to the model to decide the quality of the code?
    • isolay 2 hours ago
      You unlock this feature by subscribing to the Premium Gold plan.
      • AndrewVos 1 hour ago
        Please email us to talk Enterprise Plan pricing, actually.
  • 8-prime 5 hours ago
    Does this actually relate to the code quality being observed by the agent? The readme isn't very clear on that IMO. I have some projects I'd love to try this out on, but only if I am to get an accurate representation of the LLMs suffering.
  • hansmayer 1 hour ago
    In the absence of real productive use cases for AI agents, I guess plugins to anthropomorphise them fruther will have to do.
    • sixothree 1 hour ago
      How so?
      • hansmayer 1 hour ago
        How so what? 6 years in, we're still looking for that flood of new innovative apps and one-man billion dollar startups. Instead we got a flood of sh*t content, embarassing outages and "AI workflows" - which no one can quite describe. Or did you have something else in mind?
        • sixothree 43 minutes ago
          You're being over-opinionated for something you don't understand.

          You should really try these tools out with an open mind. I know you won't take that last bit of advice, so this makes you not worth my time. But I can tell you this - these tools make people productive in ways you aren't understanding.

  • xydone 1 hour ago
    Maybe I'm the person who yells at clouds but I find the personification of LLMs, for lack of better, less strong words, horrific.
  • greg_dc 5 hours ago
    Honestly, I don't care about Opus 4.7. This is the true evolution of agentic coding.
    • AndrewVos 1 hour ago
      Thank you, I hope my investors feel the same.
  • coldcity_again 5 hours ago
    I really want this! Any chance of a Cursor version?
    • AndrewVos 4 hours ago
      I just added a cursor plugin to the repo, let me know how it goes!
    • sixothree 1 hour ago
      People are continuing to use Cursor?
      • nrclark 21 minutes ago
        out of curiosity - any reason not to use it?
  • philipwhiuk 3 hours ago
    • AndrewVos 1 hour ago
      Excuse me, that's our IP!
  • j_gonzalez 26 minutes ago
    [dead]