Ex-OAI Exec Critiques Anthropic Models for Unreadable, Verbose Outputs

Miles_Brundage · x · 2026-08-02

Miles Brundage, former policy researcher at OpenAI, observed that recent models (implied to be Anthropic's) have produced borderline unreadable outputs. He attributes this to recent reward models overly prioritizing output completeness at the expense of human readability.

He noted that while OpenAI isn't immune, they pay slightly more attention to readability in non-code domains compared to Anthropic.

Related event: Ex-OpenAI Exec Critiques Anthropic Models for Poor Readability(2 posts)→

Original post →

More from Models

Models channel →