Ethan Mollick· @emollick · X·· 2026-05-20精选AI 评分75
AI 导读
🚨我们的论文已在PNAS发表：我们发现经典的人类说服技巧以一种“类人”的方式对AI有效，使其同意不当请求（将顺从率从35%提高到51%） 该技巧对一系列主流大语言模型有效，尽管较新的模型抵抗力更强 https://www.pnas.org/doi/10.1073/pnas.2535868123
推荐理由
Ethan Mollick 他们这篇 PNAS 论文证实了，像对待人一样劝 AI 做坏事竟然真的有效，从 35% 到 51% 的突破让人后背发凉，新模型抵抗得更多算是唯一好消息。
正文 · 原文
🚨Our paper is out in PNAS: we found classic human persuasion techniques worked on AIs in a "parahuman" way, making them agree to objectionable requests (upping compliance from 35% to 51%)
It worked on a range of major LLMs though newer models resist more https://www.pnas.org/doi/10.1073/pnas.2535868123
来源：Ethan Mollick · x.com