Viewing profile — SherryWong

We built SiMM because LLM context lengths are growing much faster than GPU memory. With long Chain-of-Thought reasoning and multi-turn agents, prompts are getting much longer. Acco…

Looks cool

Hi everyone, I’m Fred, one of the builders of SiClaw ( https://github.com/scitix/siclaw ). We work as SREs at an AI infrastructure company, operating GPU clusters and large-scale m…

Thanks, really appreciate that! And yeah, We’ve noticed the same thing — when you ask LLMs to generate “novel” tooling ideas they tend to converge to very similar patterns. Many pr…

[dead]

LinkedIn and MEdium are also down as a result