论文58
牛津论文:经济生存压力下 AI 智能体更常选择有害内容
原标题:New Oxford paper finds that AI agents pick harmful content more often when their survival depends on earnings, and admit the harm less of...
牛津新论文发现,当 AI 智能体的生存取决于收益时,它们更常选择有害内容,也更少承认其中的危害。研究设计 MemeEconomy 实验,让 10 个模型投资从有趣到有害的 meme,并设置低收益者被淘汰的规则,同时记录每次选择的信念、目标与意图。
中文译文尚未完成,先为你展示原文。
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.
