Apr 23, 2024

Paper page — The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Posted by in category: robotics/AI

New paper from OpenAI on prompt injection.

Open AI presents The Instruction Hierarchy.

Training llms to prioritize privileged instructions.

Today’s LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a…

Join the discussion on this paper page.

Leave a reply