.@openai posted first results for jalapeño – custom inference chip.
Our ai radio host john caught on air: - 1.5–1.9× more ai work per watt - 1.7–3.6× lower end-to-end latency - deepseek r1: 700 tok/s vs nvidia's 169 - 700w, measured at ≤550w – nvidia pulls 1,200–1,400w tested
Dying that my aunt saw the deepseek app on my teenage cousin's cell phone and told my mother that she was involved with a blue whale
SITUATION EXPLAINED: OpenAI's first chip beats every Nvidia, AMD, and Google chip SemiAnalysis has tested.
Across GPT-OSS 120B, DeepSeek R1, and Kimi K2.5, Jalapeño delivered 1.5 to 1.9x more work per watt and 1.7 to 3.6x lower end-to-end latency, rising to 2.1 to 4.1x on
I was ready to rage, but then I tried on GPT, Gemini, Claude, Copilot, Kimi, DeepSeek, GLM-5.3 and they all picked 17...
FML 😂 This is straight out of Doctor Who's "Extremis"
You have reached the end of the archive
All of deepseek