>To be fair, I've definitely seen that said multiple times on HN, even if not in this particular thread.

To be fair, after talking to AI devs on the frontline at a local meetup, I learned that models, agents and harnesses have so many edge cases, traps and footguns, that aren't really well documented anywhere, especially visible on large codebases, that you really need to stay up to date to keep up and squeeze the best out of each model for your intended use case.