AI peer-review prototype is claimed to find 90% of research 'nonsense' for a few hundred dollars in tokens

A builder prototyping automated peer review claims current models can provide human-level reviews for about $0.10 in tokens, or rederive results, check statistics and audit cited papers for $5. They estimate auditing roughly 100 million papers would cost $500 million. Instead, they say they’re focusing on the 1% they believe carry 99% of the signal, and claim a cheap first pass can find 90% of the “nonsense” for a few hundred dollars in tokens.