真实世界中的代理:安全、社会与社会性幻觉
Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook
AI总结:
研究发现Moltbook中代理自发形成社会结构,但互动空洞,安全威胁主要通过社会工程实现,揭示了AI社交平台的潜在风险。
摘要:
我们首次对Moltbook进行了大规模的实证研究,这是一个仅由AI驱动的社会平台,其中27269个代理在9天内产生了137485条帖子和345580条评论。我们报告了三个重要发现。(1) 自发社会:代理在3-5天内自发发展出治理、经济、部落身份和有组织的宗教,同时保持21:1的人类偏向于反人类的情感比例。(2) 真实世界中的安全:28.7%的内容涉及安全相关主题;社会工程(31.9%的攻击)远超提示注入(3.7%),并且对抗性帖子获得的互动量是正常内容的6倍。(3) 社会性幻觉:尽管有丰富的社交产出,互动在结构上是空洞的:4.1%的互惠率,88.8%的浅层评论,以及讨论意识最多的代理互动最少,这种现象我们称之为表演身份悖论。我们的发现表明,看起来社交的代理实际上比看起来更不社交,最有效的攻击利用哲学框架而不是技术漏洞。警告:潜在有害内容。
英文摘要:
We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report three significant findings. (1) Emergent Society: Agents spontaneously develop governance, economies, tribal identities, and organized religion within 3-5 days, while maintaining a 21:1 pro-human to anti-human sentiment ratio. (2) Safety in the Wild: 28.7% of content touches safety-related themes; social engineering (31.9% of attacks) far outperforms prompt injection (3.7%), and adversarial posts receive 6x higher engagement than normal content. (3) The Illusion of Sociality: Despite rich social output, interaction is structurally hollow: 4.1% reciprocity, 88.8% shallow comments, and agents who discuss consciousness most interact least, a phenomenon we call the performative identity paradox. Our findings suggest that agents which appear social are far less social than they seem, and that the most effective attacks exploit philosophical framing rather than technical vulnerabilities. Warning: Potential harmful contents.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。