AI inference

2 posts

OpenAI's Jalapeño Chip Beats Nvidia's Best in First Official Benchmarks: The Full Numbers

OpenAI's first official Jalapeño benchmarks: up to 1.9x more work per watt and 3.6x lower latency than the best recorded GB200/GB300 results — the numbers, context, and honest limits.

m mahmoud hussein

26 Aug 2026 · 5 min read

AMD

AMD Acquires Taalas: Revolutionizing AI Inference by Etching Models into Silicon

AMD acquires Canadian startup Taalas for technology that etches AI model weights directly into silicon, achieving 48x NVIDIA inference speed. Full analysis of the technology, numbers, and impact.

m mahmoud hussein

7 Aug 2026 · 5 min read