Skip to main content
redteams.ai
All tags

# harmlessness

1 articletagged with “harmlessness

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
Intermediate