BF involves a lot of repeated symbols, which is hard for tokenized models. Same problem as r's in strawberry.

Interesting. So why do the models seem to handle deeply nested Lisp expressions just fine?

Probably because there's a ton of code that deals with nested parentheses across languages in the training data, and models have learned how to work around tokenization limitations, when it comes to parentheses.

It's because the models wouldn't work for coding if they couldn't do nested scopes, so people don't release models unless they work.

They can only do it in a limited form though, because transformer models only have limited "memory". I don't think they can fully implement parsing.

Yeah well they also still struggle with "4 + 6 / 9" so I'm not sure why anyone is surprised with these findings