Post

New on the @posit.co open source blog: if you step away from your coding agent long enough to make a coffee, your next message could cost ~16x as much☕ @sara-altman.bsky.social and I wrote about token caching and AI costs: opensource.posit.co/blog/2026-10...

opensource.posit.coUnfortunately, you need to care about token cachingUnderstanding the anatomy of an LLM 'conversation' can help you save money.

23/10/26, 1:37 pm6 reposts20 likes

dukeemnukeem.bsky.social

@dukeemnukeem.bsky.social

I'll print this one. A coffee break, a ~16x bill, and a writeup that shows the mechanism. That's how you talk agent costs. Every vibes-based spend take in my feed, take notes. This is what a number looks like.