跳到正文
Lisan al Gaib· @scaling01 · X·· 11 小时前AI 评分58
AI 导读

Anthropic 发布原型系统 FlashProve 及配套技术报告,主题为大语言模型的可证明推理进展。可证明推理让模型提供方能在不公开模型权重的前提下,证明某段输出由特定模型生成,而非更弱的、经蒸馏或其他方式篡改的版本。报告由 Frontier Red Team 于 11 月 2 日发布。

正文 · 原文

Anthropic is preparing to pace the frontier with provable inference

They just released their prototype system FlashProve alongside a technical report

Provable inference gives model providers a way of proving that some output is generated by a certain model, and not some weaker, distilled, or in other ways tampered with version, without revealing the model weights

来源:Lisan al Gaib · x.com