Sphax

> we've been able to automatically aggregate context from pi sessions

what do you mean by this ? do you rewrite the context in your proxy ?

Sphax

2 か月前議論

That is some insane value. I've been using GLM Coding Plan Max with GLM 5.1 for a while and i've tested DeepSeek V4 Pro maybe for 3 weeks now and I found it to be better than GLM 5.1 for complex coding tasks. I've used 65m tokens and with that price it cost me $1.5, that's really cheap.

Sphax

9 か月前議論

We run Harbor and mirror every base image using its Proxy Cache feature, it's quite nice. We've had this setup for years now and while it works fine, Harbor has some rough edges.

Sphax

2 年前議論

templ is great, it's been my go to when working on web stuff with Go.

投稿

SWE-1.5: Our Fast Agent Model

GLM Coding Plan

コメント