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.

Hey Marvin, update my TODO list with action items from that latest email from Julia

Everyone else wants this too! There's a lot of exciting work happening in this space right now.

Unfortunately, the prompt injection class of security vulnerabilities represents an enormous roadblock in safely deploying and using these …

ai ai assistant ai assistants assistant assistants building chatbot data email generativeai hey julia language language model large language model list llm llms private data prompt promptengineering prompt injection promptinjection questions security security vulnerabilities space systems tools vulnerabilities work