Skip to content
Jailbreaking Humans vs Jailbreaking LLMs
josephthacker.com | blog | #ai-security | #cloud | #social-engineering | #jailbreak | #llm | #prompt-engineering | #context-window
Summary
rez0 argues that jailbreaking an LLM mirrors social-engineering humans: both fixate on recent input without full context. He predicts near-infinite context windows could make jailbreaks far harder.
- Published
- Collected