The Decoder· Matthias Bastian·· 3 小时前AI 评分58
Anthropic 称其未公开模型能力与对齐均强于 Mythos 5.1
Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1
AI 导读
Anthropic 复盘英国 AI Security Institute（AISI）的一项网络安全测试，称其内部未公开模型在能力与对齐两方面都强于 Mythos 5.1。
来源：The Decoder · the-decoder.com