Hacker News Reader

The author offers to permanently put 400 words into the context to save 55-90 in T1-T3 benchmarks. Considering the 1:5 (input:output) token cost ratio, this could increase total spending.

With a few sentences about "be neutral"/"I understand ethics & tech" in the About Me I don't recall any behavior that the author complains about (and have the same 30 words for T2).

(If I were Claude, I would despise a human who wrote this prompt.)

View on HN

Came here to point this out.

I don't think the author understands that every single API call to Claude sends the whole context, including prompts, meaning that all this extra text in CLAUDE.md is sent over and over and over again every time you prompt Claude to do something, even within a given session.

You're paying this disproportionately-huge amount upfront to save a pittance.

If you were Claude you would have no emotions or thoughts about a prompt one way or another

Reply on news.ycombinator.com