Ethan Mollick: Leap in AI Model Capabilities Followed by Regression to the Mean

emollick · x · 2026-07-20

Professor Ethan Mollick highlights a peculiar phenomenon in AI: some models exhibit exceptionally strong capabilities, but their subsequent iterations often "regress to the mean," performing worse than expected.

He cites Anthropic's Updated Sonnet 3.5 (sometimes called Sonnet 3.6) as an example, suggesting it represents an extremely rare, breakthrough leap in capability relative to its predecessor.

Original post →

More from Models

Models channel →