That was my assumption too (not that long ago, laggard that I am), so I expected LLMs to be less good at Common Lisp than, say, Javascript or Java, and surely to suck at Arc (the Lisp that HN is written in). But it's not so. They excel at Common Lisp—which, ok, has decades of history and documentation which the models have all slurped up. But they're even good at Arc, which is pretty far down the long tail. And when they mess up, I put something in agents.md and that issue mostly just goes away.

Not quite, though there does seem to be an advantage for a popular language. Dan Luu explored this at https://danluu.com/pl-tokens/

That really hasn't been my experience, LLMs have done well with Julia since Claude 3.7