OpenAI Blog · Apr 19, 2024
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
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 model's original instructions with their own malicious prompts. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions' affects your current setup before relying on it in production.
ai