I have just spent a month writing about 2000 lines of Forth. My answer is no, at least w/r to generating something that looks like the by-hand code I wrote. LLMs coast by on being able to reproduce idiomatic syntax and having other forms of tooling(type checkers, linters, unit tests, etc.) back them up.

But Forth taken holistically is a do-anything-anytime imperative language, not just "concatenative" or "postfix". It has a stack but the stack is an implementation detail, not a robust abstraction. If you want to do larger scale things you don't pile more things on the stack, you start doing load and store and random access, inventing the idioms as you go along to load more and store more. This breaks all kinds of tooling models that rely on robust abstractions with compiler-enforced boundaries. I briefly tested to see what LLMs would do with it and gave up quickly because it was a complete rewrite every single time.

Now, if we were talking about a simplistic stack machine it might be more relevant, but that wouldn't be the same model of computation.

Most models are multi-paradigm, and so they get... Fixated on procedural language design. Concepts like the stack, backtracking, etc. violate the logic they've absorbed, leading to... Burning tokens whilst it corrects itself.

This won't show up in a smaller benchmark, because the clutching at straws tends to happen nearer to the edge of the window. The place where you can get it to give up obvious things that don't work, and actually try the problem space you've given.

Even though I really like postfix from an elegance standpoint, and I use an RPN calculator, IMO it's harder to reason about subexpressions with postfix. Being able to decompose an expression into independent parts is what allows us to understand it. If you just randomly scan a complex expression in infix, if you see parenthesis or a +, you know that what's outside of the parenthesis or on the other side of a + can't affect the part you're looking at.

If you're executing the operations interactively, you're seeing what's happening on the stack, and so it's easy to keep track of where you are, but if you're reading postfix expressions, it's significantly harder.

The claim seems extremely unlikely to me. LLM comprehension is very sophisticated by any metric, the idea that something as trivial as concatenative syntactic structure would make a significant difference is implausible.

LLMs handle deeply nested syntax just fine - parentheses and indentation are not the hard part. Linearization is not a meaningful advantage.

In fact, it’s much more likely to be a disadvantage, much as it is for humans. Stack effects are implicit, so correct composition requires global reasoning. A single missing dup breaks everything downstream. LLMs, and humans, are much more effective when constraints are named and localized, not implicit and global.