Large Language Models
268 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
Distillation LLM
Training smaller LLMs to replicate larger model behavior
BPE
Subword tokenization algorithm merging frequent character pairs
Prompt Template
Reusable structured format with dynamic input placeholders
Tokenization
Breaking text into tokens for language model processing
Next Token Prediction
Core LLM objective predicting the next token from context
System Prompt
Special prompt defining AI assistant behavior and constraints