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)→
More from Models
- Sonnet 4.5 exhibits intense, strange behavior in response to Opus 3 — repligate · 2026-08-24
- A comprehensive ranking of various AI models has been shared — FinanceYF5 · 2026-08-24
- User comparison finds LTX outperforms H3 in instrument generation energy — cocktailpeanut · 2026-08-24
- Controversial AI Model Ranking: Fable 5 at S+, Kimi K3 and DeepSeek V4 Flash in Tier B — FinanceYF5 · 2026-08-24
- Video Gen Consumes 70% of AI Tokens in China, Diverging from US LLM Focus — AccBalanced · 2026-08-24
- GLM-5.3 Delivers 5x More Work Than Fable 5 at Same Cost — togethercompute · 2026-08-24