Trendora

Constitutional AI

Assess

Techniques

A training approach that uses guiding principles to shape model behavior and outputs.

Why it's here

Placed in Assess: 2 article(s) of evidence from 1 source(s), led by framework updates, with 0 in the last 30 days. Confidence 38%.

Evidence (2)

  • 4Anthropic News·5/19/2026framework_update
    Anthropic broadens frontier AI discussions

    Anthropic said it has սկսել dialogue sessions with scholars, clergy, philosophers, ethicists, and other groups to inform how it develops frontier AI systems. The company says these conversations may help shape Claude’s constitution, training values, and evaluation priorities, with a focus on moral formation and responsible deployment.

  • 7Anthropic News·1/22/2026framework_update
    Anthropic releases a new constitution for Claude

    Anthropic has published a new constitution for Claude, a document that defines the model’s intended values, behavior, and training goals. The company says the constitution now plays a more central role in training and is being released under CC0 so anyone can reuse it freely.