naaqq

Will be later.

just got 2/18, not a native english speaker, hard for me.

I don't think it's helpful, you can already get a 99+% cache hit on claude code, just change the api settings to deepseek. I would like to use a agent built by deepseek itself using deepseek models. Deepseek should make their own agent based on their model, just like OpenAI and Anthropic.

Not all read tokens are included in the context, many of the tokens are from read cache hits. I hit it many times so it grew to 200M. The number came from the API platform.

Sorry, I was wrong here. I meant a single long session. And there’s no compression, the 1M context is only half used.

DeepSeek’s official API has a cache hit rate of over 99% if you use it continuously within the same codebase for long sessions, so it’s much cheaper than frontier models. I have an example of 200M token session in claude code.

This article said some things I couldn’t put into words about different AI tools. Thanks for sharing.

Round the squirrel only if the squirrel is still on the tree.

Start reading from the 3/4 mark, that’s the ‘how’ part

This is so cool. I like the mircoSD card idea.

It makes LLMs stronger because code is something LLMs are good at.