Large Language Models
270 views
Jailbreaking
Quick Definition
Circumventing AI safety restrictions through prompt techniques
Full Definition
Circumventing AI safety guardrails and content restrictions through clever prompt engineering.
Examples
DAN prompts, roleplay exploits, instruction override
Related Terms
prompt-injection
ai-safety
guardrails-llm
More Large Language Models Terms
Embeddings LLM
Dense vectors capturing semantic meaning of text
GGUF
File format for LLMs optimized for local inference
Constitutional AI
Training AI to follow explicit principles for consistency
Sparse Attention
Attention attending to only a subset of tokens
Quantization LLM
Reducing LLM weight precision for efficient inference
Prompt Template
Reusable structured format with dynamic input placeholders