The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- ID
- 701
- Status
- new
- Published
- 20 Apr 2024, 3:00 AM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/the-instruction-hierarchy
- Source URL
- https://openai.com/news/rss.xml
Excerpt
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.
Summary
No summary yet. It will appear after the daemon summarizes this item.