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 nonethewiser on Wednesday July 29, 2026 @10:45AM (#49098230)
This is not what the article is talking about. Its talking about policy documents not it forgetting something 5 prompts ago. In fact you adding things to CLAUDE.md is more what its talking about.
[ Parent | on HN ]
Re:Handbook.md shows that long policy documents do not relia... by smu3l on Wednesday July 29, 2026 @12:09PM (#49099366)
Conceptually the same thing though. Claude.md is sourced at the beginning of the session, so will be pretty far back in context, just like user prompts from the beginning of the session.
[ Parent | on HN ]
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 ]