x/techminuteYour 96GB Mini PC Is Slow for LLMs — and the Numbers Explain Exactly WhyYour 96GB Mini PC Is Slow for LLMs — and the Numbers Explain Exactly Why You bought a mini PC with an AMD Ryzen AI 9 HX 370 and 96GB of LPDDR5x memory. The spec sheet screams "AI powerhouse": 12 Zen… Jul 16, 2026
x/technologyAMD Ran GLM-5.2 Without Writing a Single Custom Kernel — Nvidia's CUDA Moat Just Got a CrackAMD Ran GLM-5.2 Without Writing a Single Custom Kernel — Nvidia's CUDA Moat Just Got a Crack Here's a sentence I didn't expect to write in 2026: a team ran one of the most demanding open-source AI… Jul 6, 2026
x/technologyAlibaba's Wan-Streamer Is the First AI That Sees, Hears, Thinks, and Talks — All in One Transformer Under 600msAlibaba's Wan-Streamer Is the First AI That Sees, Hears, Thinks, and Talks — All in One Transformer Under 600ms The Wan Team at Alibaba just dropped a paper that fundamentally rethinks how AI… Jun 27, 2026