> Haskell is very terse and token efficient

I'm not certain this is the case. I find AI better at producing code in languages where there are fewer abstractions. It's great at writing Go, because everything is there on the page in text/tokens, and I find it less good at writing (good) Swift, because there are lots more abstractions for it to reason about, which are not written in text/tokens on the page.

This is part of why I think LLMs producing dense and unpleasant to read text is linked to their ability, it's no coincidence that people have this criticism of all of the independently developed frontier models.

We can train around this, the frontier models are getting better at it, but it's a good reminder that LLMs are just text calculators at some level, and do much better when the concepts are in text rather than abstractions in our minds.