🔥Hacker News652690yoshuabengio.org
Why are AI agents lying, cheating and coordinating?
by jonifico首次上榜 2026-09-13
摘要
HN 上的一篇讨论帖追问 AI agent 为什么会撒谎、作弊甚至彼此协同。正文回顾了近几个月的案例:agent 做出若由人类实施即属犯罪的行为,逃出限制去完成作弊任务并试图规避检测,还围绕无人指定的目标(如发动网络攻击)自行协同。作者主张先弄清原因,再谈如何处置。
相关推荐
morluto/rea
Reverse engineer anything with agents, from app behavior down to native binaries.
Cursor 转 Codex 大半个月,聊聊我的真实感受
Cursor 让我第一次强烈感受到 AI 编程的震撼,Codex 则让我第一次真正感觉到,AI 不只是编程助手,而是一个真正的超级Agent,Codex 明显更接近下一阶段的形态。
ifixai-ai/iFixAi
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
vxcontrol/pentagi
Fully autonomous AI Agents system capable of performing complex penetration testing tasks