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。

Direct and Indirect AI Injections and Their Implications

2 点作者 kerng大约 2 年前

1 comment

yosito大约 2 年前
It seems like a good way to mitigate these attacks is to train a separate "supervisor" AI that watches all conversations for things like content policy violations and prompt injections. The supervisor AI wouldn't be a chat-based LLM, it wouldn't ever change its behavior based on prompts. Its job would basically just be to watch the chat and either approve or deny the input or output. If it did block input or output, the user could get a message in the UI explaining that a supervisor blocked the chat. For infractions too severe, it could even terminate the chat.
评论 #35373425 未加载