kamil
194 posts






@YuLin807 不需要懂代码 你只需要懂你想用它来干什么 这才是AI时代的重点


《如何在你的浏览器中打开终端教程贴》 这个法子挺适合出门在外想要远程控制家里 claude /codex 或者 vps 上的 Agent的管理项目的人。 具体食用方法,直接把引文发给给你的 Agent,告诉他“帮我参考这篇推文构建浏览器终端”! 如果你的 Agent 没有办法浏览推文,可以告诉他安装 x twitter fetch 这个开源 skill 也是我的作品之一。

Introducing GPT-Live, a new generation of voice models for natural human-AI interaction. Rolling out in ChatGPT starting today. You’ll want to turn the sound on for this one.







There’s a big misconception about how GLM 5.2 was trained. Yes, they distilled Claude and GPT 5.5 — but distillation is not how they matched Opus quality. Distillation only fixed the cold start problem in RL. RLing an agentic coding model isn’t rocket science. In simplified terms: 1. RL needs trajectories — rollouts where the model actually completed a task in some env 2. No successful trajectory on a task = zero gradient = you can’t RL it. This is the cold start problem 3. Distillation solves it. You seed your model with knowledge from a smarter one (Claude, GPT) on tasks it can’t do yet 4. Now it produces positive trajectories on those tasks 5. RL on those trajectories and hill climb agentic coding 6. At that point you no longer need to distill and can solely hill climb RL to better models This is an interesting curve. I’d argue it’s harder to get to Opus 4.8 from scratch than to go from Opus 4.8 → Fable/Mythos tier. GLM 5.2 is already producing positive trajectories, so they have plenty to RL on — they’ll keep climbing to Mythos quality without distilling any further. They no longer need American models.


















