Inspired by this article, I tried to read some tutorials on Forth. My question is whether concatenative languages are AI-coding friendly. Apart from the training data availability, the question is also whether LLMs can correctly understand long flows of concatenated operations. Any ideas?
I've experimented with it and after some initial skepticism, I've been impressed -- because a simple Forth is implemented relatively concisely, it can get a "full" picture of the language by reading the implementation. The issue I've encountered is that it tends to treat forth as a single specified programming language, using non-existent words in some specific forth. With coaxing, it can correct this, though. I may write something up, but I am interested if anyone else has experimented with this -- culturally, Forth programmers tend to be very anti-AI (and I feel a bit 'icky' about my experiments)
They can produce idioms that resemble the flow of Forth code but when asked to produce a working algorithm, they get lost very quickly because there's a combination of reading "backwards" (push order) and forwards (execution order) needed to maintain context. At any time a real Forth program may inject a word into the stack flow that completely alters the meaning of following words, so reading and debugging Forth are nearly the same thing - you have to walk through the execution step by step unless you've intentionally made patterns that will decouple context - and when you do, you've also entered into developing syntax and the LLM won't have training data on that.
I suggest using Rosetta Code as a learning resource for Forth idioms.
phreda4 has been doing cool stuff with ColorForth-likes for ages and for some reason barely gets any attention for it. Always brings a smile to my face to see it submitted here
I suggest using Rosetta Code as a learning resource for Forth idioms.