Simon Willison personal blog
The Dual LLM pattern for building AI assistants that can resist prompt injection
I really want an AI assistant: a Large Language Model powered chatbot that can answer questions and perform actions for me based on access to my private data and tools. …
- Points
- 201
- HN comments
- 109
- Submissions
- 1
- Cited by
- 11 commenters
AI & Machine LearningSecurity & Privacy2023
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| May 13, 2023 | The Dual LLM pattern for building AI assistants that can resist prompt injection by simonw | 201 | 109 |
Cited in comments
Linked from 22 Hacker News comments by 11 different people, from May 2023 to Mar 2026.
Most recent:
