精选理由
OpenAI 让 GPT-5.6 Sol 自己优化自己，运行成本降了20%，生成速度也快了15%，挺牛的。
OpenAI 部署 GPT-5.6 Sol 后，通过模型自我改进实现了效率提升。生产 GPU 内核优化使服务成本降低 20%。改进的推测解码算法使 token 生成效率提升 15% 以上。这些成果来源于模型自身运行效率的优化。
原文 · OpenAI
After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more...
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. 💬 63 🔄 49 ❤️ 598 👀 47144 📊 108 ⚡