Anthropic releases FlashProve, an open-source prototype for provable AI inference
AIAnthropic has released FlashProve, an open-source prototype that generates cryptographic proofs showing a response came from a committed AI model. On a single H100 GPU, the system proves Llama 4 Maverick at about 110 tokens per second, with proofs of about 19 MB per 1,024-token request.
AIWhy it matters.
The post explains how cryptographic proofs can verify which model served a response, with concrete speed and proof-size measurements that help readers judge its practicality.
Source details
Anthropic Research · anthropic.comPublished · added here
Original title: Progress on provable inference for large language models