Lead story
Models & availability
Latest
← Feed
Copy✕ Close copy menu
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
OpenAI states that LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions.
From the source
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.
openai.com
Visit source ↗openai.com
- Announced
- 19 Apr 2024 19:00 UTC
- Detected
- 03 Aug 2026 21:11 UTC (+836d after)