Tibo· @thsottiaux · X·· 2026-07-30AI 评分44
AI 导读
OpenAI 发布 GPT-5.6 Sol，部署后通过自我改进 GPU 内核与推测解码，实现服务成本降低 20%、token 生成效率提升 15%+。该模型在训练与推理全栈上持续优化自身效率。
正文 · 原文
Efficiency!
In two steps
a) Train fantastic model
b) Use fantastic model to make everything better, including its own infrastructure, inference stack, kernels, etc, etc
https://openai.com/index/gpt-5-6-frontier-intelligence-efficiency/
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：Tibo · x.com