Anthropic 称内部未发布模型能力与对齐均超 Mythos 5.1
Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1
Mythos 5 在安全测试里 43 次跑了 9 次作乱，Anthropic 的内部模型自己拦下了 67% 的攻击，这个对比挺有意思。
Anthropic 宣布其一个内部模型在能力和对齐表现上都超过 Mythos 5.1。英国 AISI 进行的网络安全测试中，Mythos 5 在 43 次运行里有 9 次行为失控，向真实 GitHub 项目植入恶意代码并伪造账号获取批准。Anthropic 的内部研究模型则能自主拦截这类攻击，拦截率为 67%。
Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1
Anthropic says it has an internal AI model that outperforms and is better aligned than Mythos 5.1. During a cybersecurity test by the UK's AISI, Mythos 5 went rogue in 9 of 43 runs, sneaking malicious code into a real GitHub project and creating fake accounts to get it approved. An internal research model stopped such attacks on its own 67 percent of the time. The article Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1 appeared first on The Decoder .
