Ex-OpenAI Exec Critiques Anthropic Models for Poor Readability

Former OpenAI policy researcher Miles Brundage criticized recent Anthropic models for producing nearly unreadable text. He attributed this poor readability to recent reward models over-emphasizing certain metrics at the expense of conciseness.

2026-08-02 ~ 2026-08-02 · 2 related posts

• AI Researcher Criticizes Anthropic's New Models for Unreadable Outputs — Miles_Brundage · 2026-08-02

1 near-duplicate retellings: Miles_Brundage