Inference
GPT-5.6 Rewrote Its Own GPU Kernels
OpenAI cut GPT-5.6 Luna 80 percent on July 30, three weeks after general availability, funded by Sol rewriting OpenAI's own production GPU kernels and its speculative-decoding draft model. The transferable part is not the discount, it is FpSan, the floating-point sanitizer built to verify kernels no human read line by line.
Marco Kotrotsos·31 Jul 2026·6 min read
