🚨 AI News | TestingCatalog@testingcatalog

2026-05-23 06:21·41天前

AI 摘要

Anthropic在Project Glasswing项目最新进展中宣布，Mythos级模型在开发出更强的安全防护措施后，预计将向公众开放。此前，Anthropic与合作伙伴通过该项目已发现超过一万个关键或高危软件漏洞。这为模型后续的强安全防护开发提供了重要背景与方向。

ANTHROPIC 🔥： Mythos class models are expected to become generally available after getting stronger safeguards， according to the latest Project Glasswing update.

And in the near future， once we've developed the far stronger safeguards we need， we look forward to making Mythos-class models available through a general release.

Soon？ 👀

AnthropicLast month we launched Project Glasswing, our collaborative AI cybersecurity initiative. Since then, we and our partners have found more than ten thousand high-...

Anthropic 安全/对齐模型发布

在 X 查看原推导出 Markdown

🚨 AI News | TestingCatalog@testingcatalog · X

65导出 Markdown

2026-05-23 06:21·41天前

在 X 看原推· x.com

AI 摘要

ANTHROPIC 🔥： Mythos class models are expected to become generally available after getting stronger safeguards， according to the latest Project Glasswing update.

And in the near future， once we've developed the far stronger safeguards we need， we look forward to making Mythos-class models available through a general release.

Soon？ 👀

Anthropic