Cynthia Brumfield

metacurity.com

31 January 2026 14:33

Each week, Metacurity offers our free and premium subscribers a weekly digest of the best long-form (and longish) infosec-related pieces we couldn't properly fit into our daily news crush. This week's selection covers 1/3 www.metacurity.com/best-infosec...

Sung Kim

sungkim.bsky.social

19 December 2025 08:35

To teach us how modern LLM inference works, LMSYS gave us a readable version of SGLang where they distilled SGLang from 300K into 5,000 lines. Kept the core design, cut the complexity. Without sacrificing performance. mini-sglang github.com/sgl-project/...

John O'Reilly

johnoreilly.dev

18 November 2025 14:11

Foundation Models Framework in Swift Getting Started with On Device AI www.youtube.com/watch?v=p17H...

Mike

mikeshah.bsky.social

08 November 2025 09:18

This was fun, and credits to the dhwem3 team for making the port much easier on linux

Jia-Bin Huang

jbhuang0604.bsky.social

06 November 2025 18:38

Muon is a (relatively) new optimizer that powered large-scale training of recent foundation models, e.g., Kimi K2 and GLM 4.5. Interested in learning how it works? Check out the video here: youtu.be/bO5nvE289ec