Researcher calls OpenAI's perplexity disclosure a trap for Anthropic

Researcher David Manheim criticized OpenAI's release of perplexity figures as "sneaky and dishonest," arguing it pressures Anthropic into an unfair comparison since Anthropic's finer-grained tokenizer naturally yields higher perplexity.

2026-11-23 ~ 2026-11-23 · 3 related posts