OpenAI 让最新的 GPT-5.6 Sol 自己给自己打工，结果运行成本降了 20%、输出速度提升超 15%，看看模型怎么自己优化自己。
OpenAI 使用 GPT-5.6 Sol 模型在 Codex 环境中对自身基础设施进行优化，改进在推理和智能体循环中产生更多有用工作。生产 GPU 内核优化使服务成本降低 20%，改进的推测解码使 token 生成效率提升 15% 以上。这些改进通过复用在相同硬件上获得更大的性能提升。
We used GPT-5.6 Sol in Codex to optimize its own infrastructure and performance. These improvement...
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. OpenAI @OpenAI 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. 🔗 View Quoted Tweet 💬 49 🔄 28 ❤️ 807 👀 38895 📊 99 ⚡