Don't do this. If you have test time issues that are clogging the build pipeline, you can run a merge queue that creates ghost branches to test patches in sets rather than one by one.
Outside of a fun project to tinker on and see the results, I wouldn’t use this for anything that runs in production. It is better to use an LLM to assist you in building better static analysis tools, than it is to use the proposed technique in the article.