AI Dynamics

Global AI News Aggregator

About

SWE-1.6 Windsurf: 950 tokens/s code model

Some of us are still writing code. We just want to find our functions faster. SWE-1.6 on @windsurf
, runs at 950 tokens/s, powered by Cerebras. For the real ones.

→ View original post on X — @cerebras,