←back to thread

FAWK: LLMs can write a language interpreter

(martin.janiczek.cz)
207 points todsacerdoti | 2 comments | 21 Nov 25 10:28 UTC | HN request time: 0.644s | source
Show context
keepamovin ◴[21 Nov 25 11:09 UTC] No.46003360[source]▶
Yes! I'm currently using copilot + antigravity to implement a language with ergonomic syntax and semantics that lowers cleanly to machine code targeting multiple platforms, with a focus on safety, determinism, auditability and fail-fast bugs. It's more work than I thought but the LLMs are very capable.

I was dreaming of a JS to machine code, but then thought, why not just start from scratch and have what I want? It's a lot of fun.

replies(2): >>46003545 #>>46003596 #
64718283661 ◴[21 Nov 25 11:45 UTC] No.46003596[source]▶
What's the point of making something like this if you don't get to deeply understand what your doing?
replies(5): >>46003727 #>>46004046 #>>46004193 #>>46004632 #>>46004988 #
1. ModernMech ◴[21 Nov 25 14:34 UTC] No.46004988[source]▶
If they go far enough with it they will be forced to understand it deeply. The LLM provides more leverage at the beginning because this project is a final exam for a first semester undergrad PL course, therefore there are a billion examples of “vaguely Java/Python/C imperative language with objects and functions” to train the LLM on.

Ultimately though, the LLM is going to become less useful as the language grows past its capabilities. If the language author doesn’t have a sufficient map of the language and a solid plan at that point, it will be the blind leading the blind. Which is how most lang dev goes so it should all work out.

replies(1): >>46005189 #
2. keepamovin ◴[21 Nov 25 15:00 UTC] No.46005189[source]▶
Lol thank you for this. It’s more worth I work than i thought!