OpenAI 的 GPT-5.6-Sol 不只是聊天，能直接干复杂编程活了，比如自己重构 Next.js 服务器。想看看模型实际生产力有多强？这篇实测值得看。
OpenAI 的 GPT-5.6-Sol 模型经过两个多月在 Next.js 日常开发中的测试，表现出色。它能理解架构权衡、调查复杂 issue 报告，并在修复 bug 时考虑代码库其他部分。仅需简短提示即可指导，甚至独立完成了 Next.js 服务器的大规模重构（包括测试套件、部署测试）。相关 PR 将在 Next.js 16.3 发布后合并。
Sol for developing next.js:
Sol for developing next.js: Tim @timneutkens We've been testing GPT-5.6-Sol for over 2 months now. It’s incredibly good in my day-to-day working on Next.js. It understands architecture tradeoffs. It can investigate complicated Next.js issue reports. It considers other areas of the codebase when fixing bugs. Needs very little guidance. Short prompts are enough. There’s some big refactors of the Next.js server that it implemented end-to-end with me pointing at high level possible improvements (we have skills for how to grab our failing test suites on PRs, deployment tests, etc.) Those PRs are ready to merge after Next.js 16.3 has been released. 🔗 View Quoted Tweet 💬 18 🔄 4 ❤️ 191 👀 16497 📊 24 ⚡