Constitutional AI Alignment (opens in new tab)

Epistemological status: existential AI safety suggestions as a set of bullet pointsTL;DR We need to be clear about what behavior we’re trying to train when we align AIs — aligned behavior is not the default for an LLM whose behavior is distilled from ours, nor for an RL-trained maximizer. Anthropic published , and recently a large update in (a.k.a. “Soul Doc”). That includes not just what the AI should do, but explanations of how and why many decisions in the document were made that should he...