Simon Willison personal blog

The lethal trifecta for AI agents: private data, untrusted content, and external communication

If you are a user of LLM systems that use tools (you can call them “AI agents” if you like) it is critically important that you understand the risk of …
Points
0
HN comments
0
Submissions
0
Cited by
41 commenters

Society, Policy & Culture2025

Cited in comments

Linked from 57 Hacker News comments by 41 different people, from Jul 2025 to Oct 2026.

Most recent:

Search every comment that links here →

More from Simon Willison

All 189 posts →

Related posts from the same era