Constitutional AI
An AI training approach developed by Anthropic where models are trained to follow a set of principles or 'constitution' rather than relying solely on human feedback.
Constitutional AI is a training methodology created by Anthropic that uses a written set of principles to guide model behavior. Instead of relying entirely on human feedback to shape responses, the model evaluates its own outputs against the constitution and generates training data accordingly. This creates a feedback loop where the AI learns to align with stated values through self-critique rather than external correction alone.
Also known as
CAI