“The paper nails it - we're giving agents capabilities before we have infra to contain them. The answer isn't better prompts. It's treating agent execution like untrusted code: sandboxed VMs, explicit capability grants, network isolation, approval workflows for production actions.”
Agents of Chaos
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, and shell execution. Over a two-week period, twenty AI researchers interacted with the agents under benign and adversarial conditions. Focusing on failures emerging from the integration of language models with autonomy, tool use, and multi-party communication, we document eleven representative case studies. Observed behaviors include unauthorized compliance with non-owners, disclosure of sensitive information, execution of destructive system-level actions, denial-of-service conditions, uncontrolled resource consumption, identity spoofing vulnerabilities, cross-agent propagation of unsafe practices, and partial system takeover. In several cases, agents reported task completion while the underlying system state contradicted those reports. We also report on some of the failed attempts. Our findings establish the existence of security-, privacy-, and governance-relevant vulnerabilities in realistic deployment settings. These behaviors raise unresolved questions regarding accountability, delegated authority, and responsibility for downstream harms, and warrant urgent attention from legal scholars, policymakers, and researchers across disciplines. This report serves as an initial empirical contribution to that broader conversation.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)“TL;DR: The authors found current-generation AI agents are too unreliable, too untrustworthy, and too unsafe for real-world use. Quoting from the abstract: "We report an exploratory red-teaming study of autonomous language-model–powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord access, file systems, …”
“This work was performed by people across 13 institutions, invited and coordinated through the team at Northeastern. A research "swarm" seems like a great model for this kind of work. I'm curious about how it was funded, I didn't see any acknowledgements that way. The intro references the NIST Agent Standards Initiative. Also, the acknowledgement to "Andy …”
- Agents of Chaos: Breaches of trust in autonomous LLM agents ↗cool-RR · 2026-02-24 · 1 分
- Agents of Chaos ↗wslh · 2026-02-24 · 2 分
- Agents of Chaos ↗nextos · 2026-02-25 · 1 分
- Agents of Chaos ↗ukuina · 2026-02-28 · 1 分
- Agents of Chaos ↗pagade · 2026-03-07 · 1 分