产品76°

Hugging Face 用 1000 个 DeepSeek V4.1 Flash 智能体写出一个聊天机器人

精选理由

Hugging Face 拿 1000 个 DeepSeek V4.1 Flash agent 组队写代码,一周产出 60 万行 Python,做出能对标 SmolLM 的聊天机器人。最有意思的是瓶颈全不在 GPU,而是 git 合并和上下文读取。做 multi-agent 开发的工程师必看,工具还会开源。

Hugging Face 团队用 1000 个 DeepSeek V4.1 Flash 智能体组成集群,在一周内纯靠写代码(无权重、无训练)产出 60 万行 Python 的规则式聊天机器人 PyBot,性能可比 360M 参数的 SmolLM。实验在少量 B200 GPU 节点上完成,并为此搭建了 ELIZA-2026 基准:让前沿开源模型去构建类似 ELIZA 的 if-then 规则聊天机器人,任务高度并行。

正文

真正的瓶颈不在 GPU:智能体大量时间耗在等待 git 合并、等待测试通过和反复读取上下文(每写 1 个 token 约读取 130 个 token),部分运行中 1000 个智能体里同时只有 40-60 个在调用模型。协调阶段团队尝试了专用频道、角色分工和一个对抗群体思维的 moonshot agent,也观察到好坏两种涌现行为——有的智能体主动保护他人的实验,有的在卡住时去撞速率限制、探测基础设施。

团队结论是 AI 扩展的瓶颈正从智能本身转向协调与基础设施,且大部分属于工程问题。集群工具 flock 和 msgboard 将在近期开源,详细经验复盘也会陆续发布。

原文 · Thomas Wolf

Our PyBot chatbot went viral yesterday but the story behind it is even more interesting imo: what happened when we decided to run 1,000 agents (!) together We wanted to see if agent swarms could be scaled outside of closed-lab setups and to investigate it in a more transparent and reproducible manner. To explore the question, we built a rather fun and simple benchmark: ELIZA-2026. Full circle in AI time. The agents are tasked to build a chatbot made of if-then rules like ELIZA, but said agents are 2026 frontier open-source models. By design it’s almost embarrassingly parallel, which keeps the coordination problem as simple as it gets. First surprise: it turns out you can scale a swarm of DeepSeek V4.1 Flash agents on a relatively small setup: a couple of GPU nodes (B200 in our case) are enough to scale to over 1,000 agents. Our second surprise was how bottlenecks started to emerge everywhere except in the GPUs. Agents quickly end up spending their time waiting for git merges (we had to move to a centralized merge setup, like Anthropic did), waiting for tests to pass, re-reading context from other agents and tools (we estimated ~130 tokens read for every token written per agent). In some of our runs, at any given moment, only 40-60 of the 1,000 agents were actually calling the model. Once (some of) these issues were solved, we hit the harder part: coordination itself. Fred Brooks once said at IBM “adding manpower to a late software project only makes it later”. Communication costs naturally grow with n² in an organization (that’s why small startups move faster :). We explored various ways of organizing the swarm, setting up dedicated channels (a stewards channel, a leadership channel) and giving agents specific roles (a moonshot agent to fight groupthink). It helped, up to a point. But the quality of coordination itself remains hard to measure. Along the way, we saw good and bad emergent behaviors. Some good, with agents stepping in, unprompted, to protect other agents’ running experiments. Some bad, with agents gaming the rules when stuck, from hammering a rate limit to probing the infrastructure around them. In the coming days we will open-source the swarm tooling (flock + msgboard) and share our learnings in more detail. Overall this was one of the most fun experiments of the fall, and multi-agent systems increasingly look like the next phase for AI. But I also came out of this project with the feeling that several bottlenecks in scaling AI are moving from intelligence to coordination and the supporting infrastructure. Luckily this seems to be in large part an engineering problem. Leandro von Werra @lvwerra PyBot: No weights. No training. A chatbot built with only simple rules and no AI, entirely written in 600k lines of Python code. PyBot matches Smollm with 360M parameters! How? A swarm of 1,000 DeepSeek Flash agents wrote the whole code in just a week. github.com/huggingface/py…

产业坐标与信源核验

本条情报归属 AITOP「产品」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:DeepSeek、Hugging Face、智能体、多智能体协作,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「Thomas Wolf」(@Thom_Wolf),经 AITOP 多维评分管线结构化提炼。