Day 4 – Don’t use Forsyth-Edwards Notation to play chess with LLMs
The article showcases utilization of Raku’s LLM-related functionalities: chatbooks, LLM-functions, and LLM-prompts.
Remark: This article was originally written as a Jupyter notebook. A few type of “magic” cells are used. Hence, some of the cells below contain start with comment lines that are actually magic cell specifications. Here are a few such specs: #%js, $% chat cm, #% markdown, etc.
There are plenty of (research) articles, posts, software packages, or coding projects about LLMs-and-chess. (For example, see [DM1, NC1, NCp1, MLp1].)
In this article the focus is not on playing chess well by LLMs. Article’s main message is that Raku can be used to facilitate chess playing, exploration, or puzzle solving. (With LLMs or otherwise.)
Remark: The functions is-fen-string and fen-specs-by-predicate are useful if 3rd party chess notation packages are used. (Not necessarily Raku-grammar based.)
