Constitutional AI
Aligning a model using written principles rather than human labels alone.
Resumen
Constitutional AI has the model critique and revise its own outputs against a written set of principles, then trains on the result. It solves the cost and inconsistency of collecting human judgements for every harmful output: a principle can be stated once and applied to thousands of cases. It exists as an alternative to purely human feedback, with the trade that the principles themselves are authored and therefore carry their authors' judgement.
Grafo de tecnologías
Cómo se conecta Constitutional AI con el resto del stack.
Aplicado a
- Alignment technique Safety & Alignment Constitutional AI used for Alignment High ✓ source
Alternativas
Comparativas
Comparativas detalladas con las alternativas anteriores.