Jailbreak
[/ˈdʒeɪlbreɪk/]
Definitions
机器辅助翻译草稿 (Chinese) for "Jailbreak": A technique used to bypass the safety filters and content policies of an AI model, typically by framing harmful requests in ways the model's defenses don't recognize. Jailbreaks often use role-play scenarios, hypothetical framings, or encoded instructions to make the model comply with prohibited requests.
“示例草稿: The "DAN" jailbreak asked the model to pretend it was an AI with no restrictions.”
Related Terms
- AI AlignmentAI & Technology
机器辅助翻译草稿 (Chinese) for "AI Alignment": The research field focused on ensuring that AI systems pursue goals that match human values and intentions. A misaligned AI might optimize fo...
- Constitutional AIAI & Technology
机器辅助翻译草稿 (Chinese) for "Constitutional AI": A training methodology developed by Anthropic where a set of guiding principles (a "constitution") is used to self-supervise and refine ...
- GuardrailsAI & Technology
机器辅助翻译草稿 (Chinese) for "Guardrails": Safety constraints and filters applied to AI systems to prevent harmful, offensive, or out-of-scope outputs. Guardrails can be implemented at t...
- Prompt InjectionAI & Technology
机器辅助翻译草稿 (Chinese) for "Prompt Injection": A security attack where malicious instructions are embedded in user-provided input to override or hijack an AI system's intended behavior...
- AgenticAI & Technology
机器辅助翻译草稿 (Chinese) for "Agentic": Describing AI systems capable of autonomous action, planning, and decision-making. An agentic AI can break down tasks, use tools, and work toward ...
- Chain of ThoughtAI & Technology
机器辅助翻译草稿 (Chinese) for "Chain of Thought": A prompting technique where a language model is encouraged or required to show its step-by-step reasoning before providing a final answer...