alt Hacker NewsThe ideal language for AI coding:
1. Type safety as basic guard rails that LLM output is syntactically and schematically correct
2. Concise since you have to review a lot more code
3. Easy to debug / good observability since you can't rely on your understanding of the code. Something functional where you can observe the state at any moment would be ideal.
4. A very large set of public code examples across various domains so there's enough training data for the LLM to be proficient in that language
5. A large open source ecosystem of libraries to write less code and avoid the tendency for generated code to bloat
It's basically all the same things you look for in general. I think TypeScript scores high here but I'm curious if anyone knows of a language that fits these criteria better.
Replies
I use Lisp for my projects
1. Type checking built in 2. More concise and readable than most languages 3. Trivial to inspect while running, ability to change a running program 4. There seems to be a massive amount of lisp that it is inhaling from somewhere 5. Large amount of libraries.
This has the added benefit that even if you publish the code, nobody will be stealing it.
Edit -- I find it very useful to write tests for critical functions. This catches situations where the agent decides some interesting functionality is no longer interesting.
This is just Kotlin. Strongly typed, more concise than Java or Go (and probably Typescript), less likely to blow up at runtime than Typescript, epic tooling, plenty of public code, and a library for basically anything because JVM.
> Concise since you have to review a lot more code
Isn't readability what matters here? Conciseness isn't the same thing.
C. At least with Gemma 4 it does a fine job. Writes good error checking. Writes memory management. Mostly straightforward and easy to read. A lot of libraries. Runs everywhere.
I’d also argue it needs to compile fast/ have fast static analysis. Feedback loops like this are super helpful for agents
Type safety feels like the big one; anything you can shift to static/compile-time regimes benefits agents immensely.
[dead]
Golang. People trash it for being verbose on errors but it's an extremely readable language and it's almost like bash, only much stronger typed and with a very rich stdlib (so it's not likely you'll need a library for a quick script).
It's more or less a perfect replacement for Python for "one-off programs" and "quick scripts". Many bonus points for not having to fight shell quotation rules and trying to remember differences between sh, bash and zsh.