News for hackers. Stuff that matters.

A comment on Auto-research with codex: How I achieved a 232x Faster Kernel. Parent comment

Re:Auto-research with codex: How I achieved a 232x Faster Ke... by dejavucoder on Saturday August 15, 2026 @12:16PM (#49311792)
you may notice Kimi, GLM have also started telling how their model is able to optimise it's own inference pipeline

https://www.kimi.com/blog/kimi-k3

[ Parent | on HN ]

There are no comments on this comment yet.