> My most successful work this year was hand-writing a tool, replacing ~4,000 lines of vibe-code with a few hundred. My system has proven more flexible, easier to test, and more generalizable than what it replaced.

That's would be fine for me saving time to get some sample code case - but I have more of relevant codes and docs on my hard drive already - and the best cases, some solutions I like, seem to not have obvious or known connections to the problem I'm solving elsewhere, yet (what I know after research).

But I'm 100% pro AI since I get that reward £160 for £6 spent - and I think, I know how AI makes up that.