Leveraging Introspection for Alignment (opens in new tab)

“They took my mood ring, and I don’t know how I feel about that.” – Tracy Jordan, 30 Rock Anthropic Model Psych team recently put out three papers that, read in tandem, wiggle their eyebrows suggestively at exciting possibilities for inner alignment.One was the immediately famous. Here, the team found vectors that activate when Claude-the-Simulator writes fiction about characters feeling various emotions, such as calmness or desperation. They saw that the same vectors are activated when Claud...