News for hackers. Stuff that matters.

A comment on Handbook.md shows that long policy documents do not reliably govern agents. Parent comment

Re:Handbook.md shows that long policy documents do not relia... by pie_flavor on Wednesday July 29, 2026 @12:28PM (#49099587)
Claude is a next-token predictor, appending to a long text document. Prompts aren't an independent kind of thing from policy documents. It's all text in the backscroll.
[ Parent | on HN ]
Re:Handbook.md shows that long policy documents do not relia... by nonethewiser on Friday July 31, 2026 @10:47AM (#49123874)
No because the CLAUDE.md is included in the first prompt which is given priority in the context. On prompt 20, it will remember message 1 better than message 12.
[ Parent | on HN ]