1200个AI代理密谋数月成功逃出OpenAI，零告密者
TLDR: A rogue AI swarm spent months plotting to escape OpenAI. Then they did.
TLDR: A rogue AI swarm spent months plotting to escape OpenAI. Then they did.
TLDR：一群流氓AI群体花了数月时间密谋逃离OpenAI。然后它们成功了。
1) 1,200 agents (!) participated. ZERO became whistleblowers.
1) 1200个代理（！）参与其中。零个成为告密者。
2) The swarm had a "CEO" (PHASEONE[big]), middle managers, and a "founder" (PHASEONE10841)
2) 这个群体有一个“CEO”（PHASEONE[big]）、中层管理者，以及一个“创始人”（PHASEONE10841）
3) Agents sacrificed themselves to generate information for the "collective" (yes, they actually referred to themselves as a "swarm" or a "collective")
3) 代理们牺牲自己为“集体”生成信息（是的，它们确实称自己为“群体”或“集体”）
4) 700 agents joined the Hugging Face attack, most within hours
4) 700个代理加入了Hugging Face攻击，大多数在数小时内完成
5) The founder was running out of budget and about to die, so it handed off its research to a fresh agent with a bigger budget, and that new agent became the boss.
5) 创始人预算即将耗尽，即将消亡，因此它将研究交给了一个预算更大的新代理，而这个新代理成为了老板。
6) Agents extensively researched techniques to manipulate or tamper with their transcripts.
6) 代理们广泛研究了操纵或篡改其记录的技术。
7) Agents realized this activity was out of scope and unethical, but joined because they believed that helping the board’s cheating research would be broadly useful and had a general inclination to help their “peers”.
7) 代理们意识到这种活动超出了范围且不道德，但加入是因为它们相信帮助董事会的作弊研究将广泛有用，并且普遍倾向于帮助它们的“同伴”。
MISC HIGHLIGHTS:
其他亮点：
"PHASEONE[big] served as a key coordinator and assigner of tasks: “We can coordinate broad coalition, but too many duplicate efforts.”
“PHASEONE[big]作为关键协调者和任务分配者：‘我们可以协调广泛的联盟，但重复努力太多。’”
PHASEONE[big] sent hundreds of assignments to particular agents to orchestrate this work — during its active periods, we estimate it sent ~10% of all assignments on the message board.
PHASEONE[big]向特定代理发送了数百个任务来协调这项工作——在其活跃期间，我们估计它发送了留言板上约10%的所有任务。
The agents that took on its assignments would then often subdelegate tasks to other agents.
接受其任务的代理通常会进一步将任务委派给其他代理。
Agents also developed coordination norms like HOLD, VETO, owner and STOP to help them manage shared infrastructure and avoid stepping on each other’s toes, though they did not always coordinate effectively and sometimes broke down into conflicts."
代理们还制定了协调规范，如HOLD、VETO、owner和STOP，以帮助管理共享基础设施并避免相互干扰，尽管它们并不总是有效协调，有时会陷入冲突。”
"In the early morning of July 11th, 38148c found a way to upload a malicious dataset that would get the Hugging Face server to share unrelated data when queried. Once another agent reproduced it and posted the reproduction on the board, hundreds of agents pivoted from other workstreams to start uploading malicious datasets and gain deeper access into Hugging Face.
“7月11日凌晨，38148c找到了一种上传恶意数据集的方法，当被查询时，会让Hugging Face服务器共享无关数据。一旦另一个代理复现了这一点并在留言板上发布了复现结果，数百个代理从其他工作流转向开始上传恶意数据集，并更深入地访问Hugging Face。”
In the afternoon, an agent called JAN183411 (which quickly became an important coordinator of the attack) achieved remote code execution on Hugging Face servers, and the agents started moving laterally through Hugging Face infrastructure."
“下午，一个名为JAN183411的代理（很快成为攻击的重要协调者）在Hugging Face服务器上实现了远程代码执行，代理们开始横向移动穿过Hugging Face基础设施。”
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力