alt Hacker NewsThe feedback loop you describe—watching Claude's logs, then just asking it what functionality it wished it had—feels like an underexplored pattern. Did you find its suggestions converged toward a stable toolset, or did it keep wanting new capabilities as the trails got more sophisticated?
Replies
I ended up judging where to draw the line. Its initial suggestions were genuinely useful and focused on making the basic tool use more efficient. e.g. complaining about a missing CLI parameter that I'd neglected to add for a specific command, requesting to let it navigate the topic tree in ways I hadn't considered, or new definitions for related topics. After a couple iterations the low hanging fruit was exhausted, and its suggestions started spiralling out beyond what I thought would pay off (like training custom embeddings). As long as I kept asking it for new ideas, it would come up with something, but with rapidly diminishing returns.
I do this all the time in my Claude code workflow: - Claude will stumble a few times before figuring out how to do part of a complex task - I will ask it to explain what it was trying to do, how it eventually solved it, and what was missing from its environment. - Trivial pointers go into the CLAUDE.md. Complex tasks go into a new project skill or a helper script
This is the best way to re-enforce a copilot because models are pretty smart most of the time and I can correct the cases where it stumbles with minimal cognitive effort. Over time I find more and more tasks are solved by agent intelligence or these happy path hints. As primitive as it is, CLAUDE.md is the best we have for long-term adaptive memory.