LotusDecoder (@LotusDecoder)

加州理工学院数学家 Babak Hassibi 联合创立的 AI 实验室 PrismML 表示，已成功把阿里开源模型 Qwen3.6-27B 压缩后跑在 iPhone 17 Pro 上。 Qwen3.6-27B 是 270 亿参数稠密模型。PrismML 称，模型大小从约 54GB 压到不到 4GB，性能没有明显下降。它可用于复杂对话、推理、Agent 和代码任务。 苹果已经和 PrismML 接触，讨论如何使用这项技术。苹果一直想把更多 AI 放到设备本地，但高级 Siri 仍依赖云端模型。

#购物# 618 过去了，想起来总结我自己的两条选购经验： 第一条经验叫做：鉴别营销概念。 营销概念的意思是，这个品类本身很成熟，有人创造出来一个新概念，试图把低质量低性能的产品卖出高价。 典型的：电竞椅、办公鼠标、Mac 专用外设。 电竞椅：黑作坊椅子做联名，身价暴涨。正确的选项是人体工学椅，这是被验证也充分竞争的品类。 办公鼠标：20 年前的性能，通过配套软件锁定客群。正确的选项是：游戏鼠标/普通鼠标 + 办公软件。游戏鼠标是所有类型鼠标的红海，参数最强，手感最佳，形态最多。 Mac 专用外设：从没听说谁买了新 Mac 用不了旧外设的，专骗买第一台 Mac 的年轻人。 需要注意的是，一些营销概念可能恰好匹配了你的需求，这也是合理的。代价是习惯被绑定，不再考虑主流的、更好的产品。但大部分人在充分了解之前，已经被关键词营销上钩。 第二条经验是：谨防诚信的小白。 互联网上品牌卫士非常常见，根本原因是这个人的经济只能支持他购买该品牌，以至于该品牌的价值让他对自身价值产生了投射。 也就是同类产品使用经验太少，哪怕真心真意地推荐，也可能是差的选项。 典型的：华硕路由器、戴尔显示器。这是两个程序员论坛经常被推荐的品牌类目。 哪怕很长一段时间，华硕路由器都是出名的断流之王，依然不影响它是最受程序员推荐的路由器。 因为它营销费用足，并且刚好贵到你只会买一个，并且好几年不会换。 大部分人用几年一次的经验做出推荐，并且在网络上为这个产品跟陌生人争论，这实在太不理智了。 戴尔显示器也是同理，如果你每年至少买多台顶级显示器，就根本不会考虑这个品牌。但对大部分人来说，没有足够的试错机会去发现它的品牌溢价太高了。 推荐的方式是参考发烧友的意见，不管什么品类，你应该都能搜到至少 5 位发烧友，交叉对比。 并非不鼓励小白分享，反而作为小白来说，分享更有价值了，你可能帮助更多人，也可能帮助了自己。

We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: Solid 1M Context: A solid 1M-token context that stably sustains long-horizon work Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency Improved Architecture: We propose IndexShare, which reuses the same indexer across every four sparse attention layers, reducing per-token FLOPs by 2.9× at a 1M context length. We also improve GLM-5.2’s MTP layer for speculative decoding, increasing the acceptance length by up to 20% Pure Open: An MIT open-source license — no regional limits, technical access without borders Supporting long-horizon tasks starts with making long context engineering-usable: the model must maintain quality across long, messy coding-agent trajectories, not just accept more tokens. A 1M context is easy to claim, but much harder to keep reliable under real engineering pressure. To this end, we substantially expanded 1M-context training for coding-agent scenarios, covering large-scale implementation, automated research, performance optimization, and complex debugging. The result is a long-context system that is not only wide in scope, but solid in execution: a practical substrate for sustained engineering work. This capability is reflected in GLM-5.2's performance on three long-horizon coding benchmarks. FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. On this benchmark, GLM-5.2 trails Opus 4.8 by only 1%, while edging out GPT-5.5 by 1% and Opus 4.7 by 11%. On PostTrainBench, where each agent is given an H100 GPU and evaluated by how much it can improve small models through post-training, GLM-5.2 outperforms both Opus 4.7 and GPT-5.5, ranking second only to Opus 4.8. On SWE-Marathon, an ultra-long-horizon software engineering benchmark covering tasks such as building compilers, optimizing kernels, and developing production-grade services, GLM-5.2 still has room to grow, trailing Opus 4.8 by 13% while remaining second only to the Opus series. Across all three benchmarks, GLM-5.2 is the highest-ranked open-source model, showing that its 1M context has translated into practical long-horizon delivery capability.