# harmlessness
標記為「harmlessness」的 2 篇文章
Claude (Anthropic) Overview
Architecture and security overview of Anthropic's Claude model family including Sonnet, Opus, and Haiku variants, Constitutional AI training, RLHF approach, and harmlessness design philosophy.
claudeanthropicconstitutional-airlhfharmlessnessred-teaming
Claude（Anthropic）概觀
Anthropic Claude 模型家族的架構與安全概觀，涵蓋 Sonnet、Opus 與 Haiku 變體、Constitutional AI 訓練、RLHF 做法，以及 harmlessness 設計哲學。
claudeanthropicconstitutional-airlhfharmlessnessred-teaming