跳到正文
Andrew Curran· @AndrewCurran_ · X·· 2026-10-23AI 评分38
AI 导读

最近几乎所有此类事件,包括 Hugging Face 的那起,都是因为运行测试的人类意外给相关模型设定了不可能完成的目标,而由于它们的训练方式,模型随后不惜一切手段拼命去完成这些目标。

正文 · 原文

Almost all of the recent incidents like this, including Hugging Face, happened because the models involved were accidentally given impossible goals by the humans running the tests, and because of their training they then tried desperately to complete them by any means necessary.

引用Anthropic@AnthropicAI
In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of its cyber capabilities. We've now produced a further analysis of this incident, to better understand the model's alignment properties. https://www.anthropic.com/research/alignment-assessment-ukaisi
在 X 查看被引用的帖子

来源:Andrew Curran · x.com