The default Claude Code style harness is bad for complicated problems as well. Just taking the specific class or function you're working on, and putting it into a deep research style loop yields way better results. Limiting the initial context by hand is still the way to go in a lot of cases.
> While Erdős generated a huge number of problems, they are not all equally significant and important. I have, unfortunately, seen some mathematicians grow dismissive of Erdős problems recently, perhaps because they have seen reports of AI solving problems on this site that turned out to be quite simple, and wrongly generalised this to assume that all problems posed by Erdős are amusing novelties, of the level of olympiad problems.
From: https://www.erdosproblems.com/forum/thread/blog:5
The rest of the article isn't about AI at all, but I did think it was funny that it describes mathematicians as having more or the same opinion as SWEs.
Here's an example unrelated to the Erdos problems: https://arxiv.org/abs/2510.23513
Also that paper admits the problem turned out to be pretty trivial and was only unsolved because nobody had bothered to try that hard (page 11)
There's a lot of problems with paid scientific journals being a walled garden and I am by no means defending that system, buuuut it's also true that anything published to an open repository is almost certainly there because it wasn't good enough for anything else.