News for hackers. Stuff that matters.
Re:Martin Fowler: Technical, Cognitive, and Intent Debt by awesome_dude on Wednesday April 22, 2026 @03:23PM (#47868083)
I often say to Claude "you're doing X when I want Y, how can I get you to follow the Y path without fail" and Claude will respond with "Edit my claude.md to include the following" which I then ask Claude to do.
Re:Martin Fowler: Technical, Cognitive, and Intent Debt by mettamage on Wednesday April 22, 2026 @04:47PM (#47869100)
Ah yea I do that too. I often have reflection sessions with Claude where I ask it "how can I make sure you do behavior X so we get outcome Y?"

It works relatively well but not always.

Re:Martin Fowler: Technical, Cognitive, and Intent Debt by sally_glance on Wednesday April 22, 2026 @07:56PM (#47870772)
Not sure this is a great idea. The model only internalized what it was trained on and writing prompts/context for itself isn't part of that. I try to keep my context as clean as possible, mostly today's models seem smart/aligned enough to be steered by a couple of keywords.