@0xLogicrw 人家说的不是你这个意思。人家明明说的是靠蒸馏的冷启动比后续的强化学习更难，一个是葱零到一，一个是从一到一百。你这一说把意思都人家的意思搞反了。
中文
Kevin Lim
1 posts
谷歌 TPU 软件工程师 Patrick Toulme 指出，外界对 GLM 5.2 靠蒸馏追平 Opus 的说法存在误解。大模型在智能体编码任务上的训练难点在于「零梯度困境」，即模型早期若无法产生正确运行路径，强化学习便无法获得梯度信号来启动参数更新。蒸馏 Claude 或 GPT-5.5 的作用，仅仅是在冷启动阶段提供种子解答以绕过零梯度困境。
一旦模型跨过冷启动门槛，后续的性能爬升将不再依赖蒸馏，而是完全依靠强化学习的爬山算法进行自我演化。Toulme 强调，GLM 5.2 已经具备独立产生成功路径的能力，完全可以通过强化学习自主迭代到更高级别，彻底摆脱对美国大模型的依赖。
Patrick C Toulme@PatrickToulme
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.
中文