Chris Olah says the persona view predicts model behavior well
Original titleThe persona view has had a lot of predictive power so far. It's pretty consistent with what we've seen from interpretability thus far.
AISummary
Chris Olah says the persona view has had strong predictive power so far and is consistent with interpretability findings. He adds that it offers comparatively actionable implications for AI safety.
Source: Chris Olah · x.comPublished · added here