‹ BackHN Continuity

Thread

Turbo Haskell

213 points · 62 comments · pjmlp

  1. dzonga · · focus · HN ↗
    now that there's all the rage about agentic coding - & languages don't matter - why r people not migrating to more less error prone languages like Haskell ?
    1. pawelmurias · · focus · HN ↗
      Agents write code in popular languages better.
    2. Gimpei · · focus · HN ↗
      Because languages don’t matter so why bother.
    3. epgui · · focus · HN ↗
      Anecdotally, I’ve found Claude-generated Haskell code to be almost as bad (hard to read) as Claude-generated python.

      I have no doubt the haskell compiles… but when it comes from an LLM it reads like nonsensical code soup.

      Claude-generated Clojure seems a lot better.

      1. tikhonj · · focus · HN ↗
        I've had much better experiences with Haskell (well, mostly PureScript for now) than Python, but that might be because I am very hands-on with the design of the core types and abstractions I'm working with.

        Having an effect system so that Claude is not tempted to throw in side-effects everywhere helps a lot too!

        1. epgui · · focus · HN ↗
          Yes, undoubtedly.

          (For further context, I was comparing essentially vibe code across languages. Vibe-coded Clojure stood out as much less unpalatable than anything else I tried.)

    4. rspeele · · focus · HN ↗
      The pre-LLM popularity of languages remains sticky because it influences what libraries are available, the sophistication of the tooling, and of course, sticky developer preferences. So while the playing fields may shift a little, it resembles what came before. Also, in my circles I've noticed it's very easy for us to rationalize why our previous favorite language is also the perfect language for the agent era.

      If your favorite language before was Python, why, LLMs are fluent in it! So much training data! So many libraries! Home of machine learning! None of that pesky compile time, agents don't need compile time safety anyway, they write such good test coverage! It's The Perfect Agentic Coding Language.

      If it was Rust, by jove, an agent can easily handle the headache of satisfying the borrow checker, and now you get the best of all worlds! Safety! Near-C runtime performance! Abstractions! The only reason people didn't use Rust before was it was Too Hard and there were Too Many Furries and now it's not hard and you don't have to interact with them, so get on board. It's The Perfect Agentic Coding Language.

      If it was Golang, oh my goodness, what a choice. Pretty fast compile time and pretty fast runtime. Agents get a tight feedback loop with build->run->test->edit. Not very complicated, code has to be written in a straightforward banging-rocks-together way. Good stable ecosystem! Rob Pike designed the language for people he said were "not capable of understanding a brilliant language but we want to use them to build good software." That's an arrogant, demeaning way to describe your colleagues but if they're LLM agents it's dead on! It's The Perfect Agentic Coding Language.

      I could go on and on. I'm not immune either! My own favorite language is F# and I play the same game:

      It has access to the .NET ecosystem like C#, but I don't have to constantly remind the agents to prefer a style with immutable data and pure functions, they idiomatically do that in F#. Files have to be in order and can only refer to symbols defined "earlier" in order, if you want mutually-referential types or functions they have to be declared as such in a joint statement, so spaghetti is hard to create: each project's codebase naturally ends up in a layered bottom-to-top architecture. The language is terse enough to be token efficient, without being symbol soup. FSX scripts can be generated during agentic code reviews to demonstrate repros for discovered issues. If there's any type of code that still warrants me jumping in and writing some myself, that code would be data type definitions/domain modelling, and F# is a joy to write those in. It's The Perfect Agentic Coding Language.

    5. cryptonector · · focus · HN ↗
      Because a) the LLMs are pretty good at Java and what not, and b) the LLMs are less good at more rarely used programming languages since there is less material on those to train on.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.