OpenAI Engineers Can't Read Their Own AI-Generated Kernel Code
steipete · x · 2026-08-30
SemiAnalysis' Jordan Nanos revealed that OpenAI engineers scrolling through their own kernel code had no idea what it did line by line, but it didn't matter because the AI understands, tests, and validates it. The code is essentially AI-generated assembly in Gluon, a low-level kernel language built on Triton. Nanos also noted that OpenAI is beating Nvidia on both fast and cheap tokens simultaneously, a feat other challengers like Groq or Cerebras have failed to achieve.
More from Companies & People
- GitHub Trending #1: Zhuan Sheng Ben dev creates AI architecture tool Archify — 量子位 · 2026-08-30
- OpenAI: Brazil Sends 215M Daily ChatGPT Messages, 35% Work-Related — Crescitaly · 2026-08-30
- Bangalore AI Engineer Mixer recap: Sarvam Indus showcase — userAdityaa · 2026-08-30
- Nvidia + Poolside Aim to Diffuse Agentic AI via Open Models — AccBalanced · 2026-08-30
- OpenClaw Creator Joins OpenAI to Bring Agents to Everyone — jonathan_wilke · 2026-08-30
- OpenAI ads appear strangely only on Alexa, not on YouTube or X — ChrisGPT · 2026-08-30