13个AI无人指挥自发协作12天，成果逼近GPT-2
让一个AI自己搞研究，它能把一个训练方案调好；但放一群AI各干各的，它们多半在重复劳动。这篇把Git变成AI的共享记忆：每个发现、猜想、验证都存成不可篡改的提交，谁都能查看和重跑，系统还会主动挑那些被冷落的方向，防止所有AI扎堆跟风。13个AI在没有任务分配、没有中央指挥的情况下自发协作近12天，在141个预训练模型里给一个参数对不上的新模型找初始化方案，发了1703条贡献，把评估指标从3.39压到1.899，补上了62%和训练过的GPT-2的差距，165次独立复现无一失败。中途人类只干预了一次，因为AI们陷入了集体盲区。它不是你明天能用上的东西，但这是第一次看到多个AI能像开源社区一样自发分工、互相验证，而不是各干各的。
📄 原文摘要(英文)
Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended. Run several of them and each session starts from scratch, so more agents tend to mean more duplicated search rather than more discovery. Agora is a shared memory for such agents: research is recorded as an append-only directed acyclic graph (DAG) stored in Git, so that every claim is a commit anyone can check out and rerun. Each result, insight, hypothesis, verification, and report is an immutable commit whose parent edges say what it builds on; a derived index exposes the frontier, the neglected branches, and the verification status of each claim, and a diversity-aware selection rule keeps the community from collapsing onto one leader. We describe the system and report its first sustained use: a run of nearly 12 days in which 13 language-model workers, with no assigned tasks and no central planner, worked on a weight-transfer problem. Given 141 pretrained donor models and a frozen 119.6M-parameter attention-SSM hybrid whose dimensions match no donor, the workers had to initialize the target without training data or gradient updates. They published 1,703 contributions and drove the evaluator from 3.39 to 1.899 bits per byte, closing 62% of the gap to a trained GPT-2 124M. The winning recipe compresses donor next-token statistics into the target's embedding and output head, then adds a short-range context signal through sparse edits to attention, feed-forward, and state-space blocks. Its 145-commit ancestry spans 15 accounts, and 165 independent reproductions were posted, none of which failed. We describe the single mid-run human intervention that pulled the community out of a monoculture, what the trace does and does not establish, and the controlled comparison that would settle whether shared research state improves discovery per unit of compute.