Functional programming accelerates agentic feature development
1–10 of 34 posts
Re: Functional programming accelerates agentic feature development
#2even if i would generally agree with the principles, no amount of markdown prompting is going to increase my confidence in agent's output and so i keep asking this question:
> what do you use for normative language to describe component boundary, function and cross-component interactions?
something i can feed into a deterministic system that will run a generative suite of tests (quickcheck/hypothesis/clojure.spec) that will either give me the confidence or give the agent the feedback.
Re: Functional programming accelerates agentic feature development
#3even if i would generally agree with the principles, no amount of markdown prompting is going to increase my confidence in agent's output and so i keep asking this question: > what do you use for normative language to describe component boundary, function and cross-component interactions? something i can feed into a deterministic system that will run a generative suite of tests (quickcheck/hypothesis/clojure.spec) th…
OP / Author here, I started closer to where you are but ended up realizing I've led a few eng teams and was never satisfied with code quality. What I COULD be satisfied by was moving our metrics in the right direction. Testing coverage, use cases covered by E2E / integration tests, P99/backend efficiency metrics, cost of infrastructure and obviously user growth along with positive feedback from Users.
That said, I don't "vibe" because it creates great code I love reading, but I can monitor and move the same metrics I would if I was managing a team.
I also use code tours a bit, and one of my first tools I needed and built (intraview.ai) was to support this need to get deep in the code the Agents were claiming was ready to ship.
Re: Functional programming accelerates agentic feature development
#4so does insisting on TDD.
I've known these things from the beginning.
Any extra restriction that still produces functional code ends up being great for LLMs to curb them deterministically.
Re: Functional programming accelerates agentic feature development
#5This article is just describing Clojure. The SUPER principals are describing the native natural way of writing Clojure, no category theory needed.
Re: Functional programming accelerates agentic feature development
#6close
Re: Functional programming accelerates agentic feature development
#7This article is just describing Clojure. The SUPER principals are describing the native natural way of writing Clojure, no category theory needed.
OP here: thanks for chiming in.
I've explored Clojure after talking to Metabase about how it had benefited them. That said, it was years ago so I can't claim it influenced this work.
The framework was designed to be a language agnostic way of sharing best practices to bias agent behavior towards a more scalable end. I initially used it when I was working with a team to do some massive refactoring/clean up across the codebase. We didn't come to an acronym but similar principles and it was "testable" and easy to push back on PRs that weren't aligned with the principles.
That said, it may be interesting to see if I could replace all that context and just say -- "code it like you would with Clojure"
Have you tried that?
Re: Functional programming accelerates agentic feature development
#8Functional programming also helped get ride of bugs before, and still people used other paradigms. Why would we change now? How to know that functional programming is indeed better for vibe coding?
Re: Functional programming accelerates agentic feature development
#9Functional programming also helped get ride of bugs before, and still people used other paradigms. Why would we change now? How to know that functional programming is indeed better for vibe coding?
It should be better for the reasons explained in the article. Pure functions require no context to understand. If they are typed, it's even simpler. LLMs perform badly on code that has lots of state and complex semantics. Those are hard to track.
In fact, synthesis of pure Haskell powered by SAT/SMT (e.g. Hoogle, Djinn, and MagicHaskeller) was already of some utility prior to the advent of LLMs. Furthermore, pure functions are also easy to test given that type signatures can be used for property-based test generation.
I think once all these components (LLMs, SAT/SMT, and lightweight formal methods) get combined, some interesting ways to build new software with a human-in-the-loop might emerge, yielding higher quality artifacts and/or enhancing productivity.
Re: Functional programming accelerates agentic feature development
#10Functional programming also helped get ride of bugs before, and still people used other paradigms. Why would we change now? How to know that functional programming is indeed better for vibe coding?
It should be better for the reasons explained in the article. Pure functions require no context to understand. If they are typed, it's even simpler. LLMs perform badly on code that has lots of state and complex semantics. Those are hard to track. In fact, synthesis of pure Haskell powered by SAT/SMT (e.g. Hoogle, Djinn, and MagicHaskeller) was already of some utility prior to the advent of LLMs. Furthermore, pure fun…
Wouldnt a fair counter argument be, that llms have been trained on way less fu ctional code though?
Like they are trained on a LOT of js code -> good at js Way less functional code -> worse performance?