I shifted over to ChatGPT-4 Code Interpreter, and it gave me a working method (and of course was able to run the code directly) using mpmath the very first go, and then with BBP when asking for using just the standard library, and also via Leibniz as well, with the warning it would be slow, when asked for the shortest code. Basically, it's still wholly inadequate for coding. Claude was willing to give me (correctly) 100 digits of Pi, but when asked to write some Python code to let me confirm the digits of Pi, it failed over and over again (in different ways each time, interestingly enough). So, I went down an interesting rabbit hole with this.
