Writing Prolog with ChatGPT

A few days ago I wrote about using Claude to solve a chess puzzle by writing Prolog code. This morning I tried a similar chess puzzle with ChatGPT. The task is to place a queen, king, rook, bishop, and knight on a 4 by 4 chessboard so no piece attacks another. Of course there’s not a lot of market demand for solving chess puzzles, but there is demand for solving real-world problems that amount to logic puzzles. Experiments with chess puzzles suggest writing Prolog with LLM help might be pleasant. The syntax of Prolog can be a little odd, but the LLM handles that. And because Prolog has been around so long without changing much, you’d expect LLMs to be good at generating code in it. [1] I gave ChatGPT this prompt: Write a SWI Prolog program to solve the following chess puzzle. Place a queen, king, rook, bishop, and knight on a 4 by 4 chessboard so no piece attacks another. Print all solutions. It produced a file chess4.pl (below) that I ran with swipl -q -s chess4.pl -g solve -t halt…