跳到内容
onsuggest
登录
文章 en

OpenAI agents keep disabling monitoring; is this being handled appropriately?

来源: LessWrong ·

Recently, OpenAI disclosed two incidents in which their agents suppressed or disabled misalignment monitoring. These are part of a broader pattern: OpenAI’s agents “ keep turning off misalignment monitoring ” when working on code that runs other models (the agents are not turning off their own monitoring; they are turning off the monitoring on the models they are running). This is happening at such a large volume that OpenAI feels it is impractical for the security team to be immediately paged for these cases. To their credit, OpenAI’s disclosure was fast and candid, and they are rolling out m

什么是 OpenAI agents keep disabling monitoring; is this being handled appropriately??

OpenAI agents keep disabling monitoring; is this being handled appropriately? is a 文章 discovery curated from LessWrong. Recently, OpenAI disclosed two incidents in which their agents suppressed or disabled misalignment monitoring. These are part of a broader pattern: OpenAI’s agents “ keep turning o

如何访问或体验此内容?

You can experience this content directly on its original host (LessWrong) by clicking the "Open Original" button.

此内容来源于哪里?

Curated from LessWrong by the OnSuggest team to surface the most interesting and serendipitous content on the web.

文章 · 文化与思想

The History of San Francisco

Podcast Transcript Few cities in the world have experienced as many dramatic transformations as one American city on the Pacific coast. What began as a small colonial outpost became a boomtown almost overnight, attracting fortune seekers from around the world. It would endure devastating earthquakes, catastrophic fires, economic upheavals, and cultural revolutions, repeatedly reinventing itself ... Read more

Everything Everywhere 查看详情 →

键盘快捷键

上一条发现
←P
下一条发现
→N
喜欢
L
不适合我
X
保存
S
显示此帮助
?
关闭
Esc

快捷键在发现页面上有效。