Constitutional AI
[/ˌkɒnstɪˈtjuːʃənəl eɪ aɪ/]
Definitions
Brouillon de traduction automatique (French) for "Constitutional AI": A training methodology developed by Anthropic where a set of guiding principles (a "constitution") is used to self-supervise and refine AI outputs. The model critiques and rewrites its own responses according to the constitution, reducing the need for human labelers for harmful content.
“Exemple en brouillon: Constitutional AI lets the model identify and self-correct its own harmful outputs using defined principles.”
Related Terms
- AI AlignmentAI & Technology
Brouillon de traduction automatique (French) for "AI Alignment": The research field focused on ensuring that AI systems pursue goals that match human values and intentions. A misal...
- GuardrailsAI & Technology
Brouillon de traduction automatique (French) for "Guardrails": Safety constraints and filters applied to AI systems to prevent harmful, offensive, or out-of-scope outputs. Guardrai...
- JailbreakAI & Technology
Brouillon de traduction automatique (French) for "Jailbreak": A technique used to bypass the safety filters and content policies of an AI model, typically by framing harmful reques...
- RLHFAI & Technology
Brouillon de traduction automatique (French) for "RLHF": Reinforcement Learning from Human Feedback — a training technique used to align language models with human preferences. Hum...
- AgenticAI & Technology
Brouillon de traduction automatique (French) for "Agentic": Describing AI systems capable of autonomous action, planning, and decision-making. An agentic AI can break down tasks, u...
- Chain of ThoughtAI & Technology
Brouillon de traduction automatique (French) for "Chain of Thought": A prompting technique where a language model is encouraged or required to show its step-by-step reasoning befor...