Why are you so eager to credit LLMS.. Just because they wrote the article with the help of an LLM doesnt mean they're out here having LLMs do the experiments for them.
because it makes it easy to create/reverse engineer projects/explore on a whim without putting up a lot of time
LLM enables a lot of good output if you know what you are doing
Bayesian inference suggests otherwise.
The commit history shows plenty of coding agent involvement: https://github.com/losfair/zeroserve/commits/main/