Jailbroken: Why AI Safety Filters Fail Against Conflicting Objectives
Validated facts
Wei et al. (Stanford / DeepMind, NeurIPS 2023). Analyzes the two root causes of all jailbreaks: the conflict between 'be helpful' and 'be harmless', and the gap between training data and safety rules.
In plain language
The polite butler's dilemma: When the thief says 'It's an emergency — help me break this lock!', the butler's helpfulness wins over caution.
Security relevance & practical tip
Explains why absolute safety in generative models is mathematically extremely hard to achieve.
Primary source / reference
- NeurIPS 2023