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.
Related event: SemiAnalysis Claims DeepSeek Kernel Code Was AI-Generated(2 posts)→
More from Companies & People
- OpenAI DevDay hands out Codex 'pet' collector cards, attendees show them off — gabrielchua · 2026-10-16
- ML researcher Emtiyaz Khan moves to TU Darmstadt, hiring PhD students via ELISS — EmtiyazKhan · 2026-10-16
- Tripo hosts first world-building hackathon in SF with World Labs and Runway talks — mhdfaran · 2026-10-16
- Dev warns enterprises: OpenAI and Anthropic products are an IP security risk — examachine · 2026-10-16
- a16z podcast: Can AI run the systems after writing the code? — a16z Podcast · 2026-10-16
- Zuckerberg backs electrician training school as US datacenter construction outpaces offices — emmanuelvivier · 2026-10-16