The Dual LLM Pattern for Building AI Assistants That Can Resist Prompt Injection §

Metadata §

• Author: Simon Willison’s Weblog
• Full Title: The Dual LLM Pattern for Building AI Assistants That Can Resist Prompt Injection
• URL: http://simonwillison.net/2023/Apr/25/dual-llm-pattern/#atom-everything

Highlights §

• 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 (View Highlight)
• So, if it turns out we can’t solve this class of vulnerabilities against the design of existing Large Language Models, what’s a safe subset of the AI assistant that we can responsibly build today? (View Highlight)