GLM-5.2 据称设计和长任务都接近 Opus，关键是加了个反奖励破解机制，让模型更靠谱。
GLM-5.2 在图形设计能力上据称达到 Opus 级别，同时在长期运行任务中表现良好。其训练引入了反奖励破解模块，用于解决强化学习中常见的奖励破解问题，例如模型走捷径、变懒、意图偏差等。该模块有助于提升编码代理在长周期任务中的可靠性与效果。GLM-5.2 是一个开源开放权重模型。
GLM-5.2 is great at design (Opus level IMO). I am also starting to see great results with long-runn...
GLM-5.2 is great at design (Opus level IMO). I am also starting to see great results with long-running tasks, too. How is this possible? I think there are a few clever hacks. But I just came across this from the official blog, and they actually trained this model with an anti-hacking module. RL, as many know, comes with this issue of reward hacking that often enables the model to take weird and suboptimal shortcuts. Not only that, but it makes the models sometimes feel like it's sometimes "lazy" or just plain "dumb" at times, including other issues like intent misalignment, verbosity, sycophancy, deception, etc. And you really don't want that for long-running tasks operated by coding agents. This is a great insight. If you use the standard /goal (in 5.5 or 4.8), you notice the models often take shortcuts that lead to long-running tasks (wasting tokens along the way) but with poor results. This is why I advocate for a focus on better verifiers. So this anti-hacking idea is a model capability that should, in theory, lead to better results on long-horizon tasks. I've seen efforts here and there in a few research papers, but haven't seen it translated to much, much less in a frontier, open-weight model. This might be contributing to some of the great results we are seeing with GLM-5.2, but I suspect there is more, of course, like better verification capabilities. It's not clear how all of these training signals lead to downstream capabilities, but this is something to look at closely with newer models. 💬 5 🔄 3 ❤️ 24 👀 2198 📊 11 ⚡