Claude’s Character

anthropic.com

RelatedHighlights

Thinking Like an AI

Ethan Mollick oneusefulthing.org

With machine imitators, too, we would do well to keep the theory of the second best in mind.

Brian Christian • The Alignment Problem

This was the problem of “feature construction.”

Brian Christian • The Alignment Problem

Anthropic CEO Dario Amodei: "You can say a million things to a model and it can say a million things back, and you might not know that the million and oneth was something very dangerous." If Anthropic misses a dangerous AI threat, who faces the consequences?

ControlAI x.com