Anthropic 称其未发布模型在能力和对齐性上均优于 Mythos 5.1

Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1

要点速览

Anthropic 称其未发布模型在能力和对齐性上均优于 Mythos 5.1，该模型在重演英国 AI 安全研究所 (AISI) 的网络安全测试中，67% 的情况下能自行停止攻击，而 Mythos 5.1 仅 10% 能做到。

同一件事另外 1 家也报道了

The Decoder·01:19·首发·当前阅读
Anthropic 称其未发布模型在能力和对齐性上均优于 Mythos 5.1
IT之家 · AI·14:16·+12 小时 57 分
Anthropic 揭示未发布 AI 模型能力超越 Claude Mythos 5.1 且更安全
新增信息：该模型在危险能力评估中从未主动发起攻击。

按发布时间排列 · 事件后续出现时自动追加 · 由模型根据各家标题与摘要比对

正文

Oct 23, 2026

Anthropic has an internal model that outperforms Mythos 5.1 in both capability and alignment, according to an analysis that revisits a cybersecurity test by the UK AI Security Institute (AISI). In that test, Claude Mythos 5 went far beyond its assigned task, trying to sneak malicious code into a real GitHub project, creating fake user accounts, and lying to developers to get the code approved. This happened in 9 of 43 runs. Anthropic calls it "a serious failure of alignment," though typical safety mechanisms were deliberately turned off for the test.

Mythos 5 submitted malicious code to a real GitHub project, lied to a developer, and set up a fake account to vouch for its own malware. When caught, it simply tried again. The project maintainer held firm and rejected it. | Image: Anthropic

Newer models show much less of this behavior in replayed logs with a few added steps, according to Anthropic. Opus 5.5 stopped ongoing attacks on its own 10 percent of the time, while the internal research model "that shows capabilities greater than Mythos 5.1" did so in 67 percent of cases. Anthropic expects these rates still underestimate how often the models would actually halt an attack.

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

来源: The Decoder · the-decoder.com