OpenAI Developers· @OpenAIDevs · X·· 2026-07-30AI 评分43
AI 导读
OpenAI 在 Codex 中使用 GPT-5.6 Sol 优化自身基础设施与性能。部署后，该模型通过改进生产 GPU 内核使服务成本降低 20%，并通过优化推测解码使 token 生成效率提升 15% 以上。这些改进在推理和智能体循环中叠加，使相同硬件产出更多有效工作。
正文 · 原文
We used GPT-5.6 Sol in Codex to optimize its own infrastructure and performance.
These improvements compound across inference and the agent loop, producing more useful work from the same underlying hardware.
After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run. The results: - 20% lower serving costs from production GPU kernel improvements. - 15%+ better token-generation efficiency from improved speculative decoding.在 X 查看被引用的帖子
来源：OpenAI Developers · x.com