跳到内容
onsuggest
登录
文章 en

Private LLM copies can agree on a secret key over a public channel

来源: LessWrong ·

Cross-posted from my blog . Epistemic status exploratory, no running protocol, theoretical estimates from a single experiment and 4 closed-weights models Two copies of the same model agree on arbitrary questions more than other models would. If the model's weights are secret, this similarity allows identical LLMs or their users to agree on a private key over a public channel with only one-way communication. Measuring agreement also allows model "fingerprinting" or self-recognition by two instances of the same model. Copies of a model could use these tools to selectively coordinate over public

什么是 Private LLM copies can agree on a secret key over a public channel?

Private LLM copies can agree on a secret key over a public channel is a 文章 discovery curated from LessWrong. Cross-posted from my blog . Epistemic status exploratory, no running protocol, theoretical estimates from a single experiment and 4 closed-weights models Two copies of the same…

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.

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。