AI 开始自己给自己做训练了
AI 界有个新工种叫「AI 同事」——不是聊天，是替你干活，而且一干就是几小时甚至几天。这篇发布了一个叫 CoworkOS 的系统，把「想怎么做」和「具体执行」分开：模型负责决策和派活，系统负责盯进度、存状态。人和 AI 改的是同一份文档、同一个 CAD 模型，你可以直接上手改，不用只靠对话。最狠的是它拿自己当试验品：让 AI 连续五轮给另一个模型做自动训练，把平均分从 33 提到 43。这不是你明天能用上的东西，但「AI 自己训练自己」这个方向，比任何聊天机器人更接近真正的自主。
📄 原文摘要(英文)
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combination that remains an open challenge. We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback. Its three-layer architecture enables direct execution or delegation to Subagents, synchronously or asynchronously, under stable responsibilities. Through a shared application layer, humans and agents inspect and revise the same evolving documents, presentations, CAD models, and Blender scenes, so human-in-the-loop participation can enter both through conversation and through direct modification of the work itself. To sustain continuity across agents and sessions, CoworkOS further introduces hierarchical workspaces and persistent semantic memory, so working files, key decisions, and long-running Job logs remain shareable, reusable, and resumable after interruption. Across 12 benchmarks and 6 categories of real-world applications, CoworkOS proves highly competitive with frontier agent applications such as Codex and DeepSeek Harness. As a sustained-work case study, CoworkOS uses GLM-5.3 as its backbone to conduct RSI-driven automated post-training on Qwen3.6-35B-A3B. Over five rounds, the model's average score across eight benchmarks rose from 33.19 to 42.95 (+9.76). Looking ahead, we believe CoworkOS opens a meaningful path toward general cowork-agent intelligence.