One thing I'd never use LLMs for, yet I use them daily, a lot, and has since Codex CLI became available, would be to write tests wholesale.

Taking a look at 1400 lines long test file: https://github.com/vm0-ai/vm0/blob/1aaeaf1fed3fd07afaef8668b... and it becomes really clear why we shouldn't yet use LLMs (without detailed reviews) for this.

Obviously, you want your tests to test the implementation, not test that the mocks are working. I didn't read all the code, but lots of it not great. Generally, you want to treat your test code as any other production code, build abstractions and simple design/architecture that lets you heavily reduce test duplication, otherwise you end up with huge balls of spaghetti that are impossible to get a clear overview of, actually reasonably change, and hard to understand what is actually being tested. Like that run.test.ts.

The whole project seems to be LLM coded, even the docs are: https://github.com/vm0-ai/vm0/blob/main/.vm0/agents/docs-wri...