Alex Sidorenko

Alex Sidorenko

@alexsidorenko.com

I make videos for devs. Human-authored articles about real agentic coding for experienced devs https://offautopilot.substack.com/about

1.1K followers30 following46 posts

Especially if you already have a lot of context in the session. Switching the model/thinking level results in the KV cache miss, making the model recompute all previous tokens On the API it costs more money, on a sub it drains your usage limits faster earendil.com/posts/prompt...

earendil.comPrompt Caching In Agents | EARENDILHow prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.

You are up to date.