Hacker News Reader

CC very regularly ignores very explicit stuff in CLAUDE.md for me, and I know I'm not the only one. The cycle of compacting/starting new conversations feels like a sisyphean spiral of the same undesirable behaviour and I've yet to find a satisfactory solution despite a lot of effort to that end.

I don't think it's fair to dismiss this article as a superficial anti-ai knee jerk. The solutions you describe are far from perfect

View on HN

Fair enough. For me compacting conversation always feels a bit weird; I have no way to tell what it effectively deleted from the context but I (very) regularly have it re-read and update CLAUDE.md as part of the process or after "discussions" with the LLM so I would guess that might be why it follows patterns in it a bit stricter for me than for most. It would be nice if the tool took care of that automatically.

Reply on news.ycombinator.com