| ▲ | giraffe_lady an hour ago |
| OCaml is the LLM secret weapon right now. They are better at writing it than they are any other language.* That’s all I have to say about it. * Other “pure” hindley-milner languages are tied but among them ocaml has some particular strengths that I’m sure others will discuss. |
|
| ▲ | nine_k an hour ago | parent | next [-] |
| Two genuine questions. (1) Why not Rust? (2) Why not Haskell? (I have my own answers, but I'd love to hear yours, too.) |
| |
| ▲ | yawaramin 3 minutes ago | parent | next [-] | | 1. Compile times. OCaml compiles very quickly (think Go) and this gives you a fast feedback loop. It lets the LLM rip through the implementation. 2. OCaml has an idiomatic approach of using interface files for all modules that can be accessed outside their libraries, and interface files give LLMs a great précis of exactly what is wanted. They then just have to follow the types and fill in the blanks to get the implementation. It's nearly the perfect use case. | |
| ▲ | giraffe_lady an hour ago | parent | prev | next [-] | | Both force the model to reason about types too much. The more constrained type system plus global inference merely holds them to what they already wrote, with very fast feedback. Rust is fine if you need it but most things don’t and ocaml has more convenient abstractions for “regular” work. If you need rust you need rust but ocaml isn’t that far off in perf. Haskell type system is too expressive, it itself becomes a place for the agent to make mistakes and get bogged down. | |
| ▲ | throwrioawfo an hour ago | parent | prev [-] | | (1) complexity (2) performance |
|
|
| ▲ | steve1977 34 minutes ago | parent | prev | next [-] |
| Did you also compare F#? |
|
| ▲ | phtrivier an hour ago | parent | prev [-] |
| Flamebait aside, has this been studied for real ? Curious how you would rate that... |
| |
| ▲ | giraffe_lady an hour ago | parent [-] | | Yes I contributed code to a paper on it this spring. It’s hard to measure and “studying” it just means feeding money into frontier models. If anyone has a few billion tokens for a couple masters students hmu so they can get it published. | | |
|
