📰 Anthropic Open-Sources FlashProve: zkSNARK Proofs That a Reply Came From the Committed Model, About 110 Tokens/s for 400B Llama 4 Maverick on One H100
Anthropic's Frontier Red Team published a research post on November 2 and open-sourced FlashProve under Apache 2.0. A model provider commits to hidden weights once, then attaches a zero-knowledge proof to each reply, so a user without the weights can check on an ordinary CPU that the reply really…
💬 What's your take? Join the discussion in the comments.
Read the original Chinese version
📰 Anthropic 开源 FlashProve：用 zkSNARK 证明回答确实出自承诺的模型，400B Llama 4 Maverick 单张 H100 约 110 token/秒
Anthropic Frontier Red Team 11 月 2 日发布研究文章并开源 FlashProve（Apache 2.0）：模型提供方先对权重做隐藏承诺，之后为每次回答生成零知识证明，用户不需要权重、在普通 CPU 上就能验证回答确实来自该模型，可用来识别中转站偷换模型或 token 流被篡改。
💬 你怎么看？欢迎在评论区讨论。