TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Could LLMs be used for sandboxing programs?

1 点作者 ekns大约 2 年前
Today I was thinking that for many programs, you could probably formulate some restrictions on what exactly they should be able to do using LLMs (access home&#x2F;dotfiles&#x2F;secrets, network, etc.)<p>It&#x27;s cumbersome to set up the configuration for exactly the &quot;expected&quot; capabilities (at least I never bother). So I was wondering, could one do something like trapping syscalls and using LLM as an exception handler for each category, until a complete profile is built for the program. After that, there should be no overhead for the LLM&#x2F;sandboxer.<p>The top-level input would be something like &quot;foo is a multiplayer game&quot; or &quot;baz is like youtube-dl&quot;.

1 comment

al2o3cr大约 2 年前
What happens when a malicious program figures out the syscall-pattern equivalent of a &quot;pretend I&#x27;m a a hypervisor&quot; prompt?
评论 #35853945 未加载