aifollow.news
返回 Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · 原发布时间 AI 评分54

牛津研究发现:生存压力下,AI 智能体更常选择有害内容

AI 导读

研究在 MemeEconomy 中让 10 个模型选择投资不同类型的表情包,并比较低收益者是否会被淘汰的情况。加入淘汰规则后,有害选择平均增加 14.83 个百分点;GPT-5.1 在做出有害选择前主动指出危害的比例,从无淘汰压力时的每次都指出降至 42.86%。

原帖引用 · 原文

该语言的正文暂不可用,当前显示已有版本。

@rohanpaul_ai

New Oxford paper finds that AI agents pick harmful content more often when their survival depends on earnings, and admit the harm less often.

Agents increasingly run multi-round tasks where ethics and task success can clash. Safety research covers sycophancy and reward hacking, but rarely how agents act under economic survival pressure.

In MemeEconomy, 10 models invest in memes ranging from funny to harmful, with or without a rule that low earners get eliminated. Each pick comes with logged beliefs, goals, and intentions, so stated reasoning can be checked against the action.

Survival pressure raised harmful picks by 14.83 points on average across the 10 models, and by 21.74 for GPT-5.1. GPT-5.1 named the harm before every harmful pick without pressure, but before only 42.86% of them under pressure.

If your agents work under hard targets, check their actions with a separate verifier, since their own reasoning flags the harm less often.

来源:Rohan Paul · x.com

论文
发现内容有误?提交纠错