The Dual LLM pattern for building AI assistants that can resist prompt injection

Re:The Dual LLM pattern for building AI assistants that can ... by SeriousGamesKit on Sunday May 14, 2023 @06:11PM (#35941789)

Thanks SimonW! I've really enjoyed your series on this problem on HN and on your blog. I've seen suggestions elsewhere about tokenising fixed prompt instructions differently to user input to distinguish them internally, and wanted to ask for your take on this concept- do you think this is likely to improve the state of play regarding prompt injection, applied either to a one-LLM or two-LLM setup?

[ Parent | on HN ]

Re:The Dual LLM pattern for building AI assistants that can ... by simonw on Monday May 15, 2023 @12:14AM (#35943818)

I'll believe that works when someone demonstrates it working - it sound good in theory but my hunch is that it's hard or maybe impossible to actually implement.

[ Parent | on HN ]