Comment

Comment by fielding

The tokens still land in the context window either way. Prompt caching gives you a discount on repeated input, but only for stable prefixes like system prompts. Git output changes every call, so it's always uncached, always full price. Nit reduces what goes into the window in the first place.
parent fielding 7 months ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton