English(EN) We’re pleased to have collaborated with AE Studio on this research.

Anthropic开发GRAM训练方法以隔离双重用途AI能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-08 23:55

Anthropic开发了一种名为GRAM的新训练方法，旨在管理具有有益和有害应用潜力的AI能力。该方法将可能危险的双重用途能力（如病毒学知识）隔离到可移除的模块中。该公司与AE Studio合作进行这项研究，旨在通过控制敏感知识的部署来增强AI安全性。 AI

影响该方法可能能够更安全地开发和部署具有敏感知识的AI模型。

排序理由该集群描述了AI实验室开发的一种新研究方法。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了AI实验室开发的一种新研究方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: safety, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 55 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

X — Anthropic TIER_1 English(EN) · AnthropicAI · 2026-07-08 23:55

我们很高兴能与AE Studio就此项研究进行合作。

We’re pleased to have collaborated with AE Studio on this research. Read more here: https://t.co/9exnFltK7A