Anthropic: Introducing The Conceptual Reasoning Index(alignment.anthropic.com)54 points by optimalsolver 2 months ago | 38 comments
How does misalignment scale with model intelligence and task complexity?(alignment.anthropic.com)228 points by salkahfi 8 months ago | 71 comments
Subliminal learning: Models transmit behaviors via hidden signals in data(alignment.anthropic.com)183 points by treebrained 1 year ago | 38 comments
