alt Hacker NewsThe best part is using harnesses like reasonix or whale make cache hit at a rate close to 98%, making requests converge to practically free. And that's with unsubsidized American providers like cloudflare or Digital Ocean.
Replies
mlazos • yesterday at 11:44 PM
How can you be hitting cache on what I think are novel LLM prompts …
➕ show 3 replies
sghiassy • today at 12:09 AM
I’ve never used either of those tools. Do they work well?
Rzor • today at 1:22 AM
Can you expand more on how you are using it?
In long form tasks, across multiple harnesses (Claude Code, OpenCode, Kimi Code, ZCode) my cache rates are typically 96-99%.
I don’t think that’s particularly out of the ordinary. Do people have different experiences with other harnesses? Which ones?