Has this got anything to do with using a stronger typed language? I've heard that reported, not sure whether it's true since my python scripts tend to be short.

Does it end in a forever loop for you? I used to have this problem with other models.

I also use Rust with Claude Code, like GP. I do not experience forever loops — Claude converges on a working compiling solution every time. Sometimes the solution is garbage, and many times it gets it to “work” by disabling the test. I have layers of scaffolding (critic agents) that prevent this from being something I have to deal with, most of the time.

But yeah, strongly typed languages, test driven development, and good high quality compiler errors are real game changers for LLM performance. I use Rust for everything now.