2026年11月3日 · 周二

An alignment assessment of the UK AISI cybertesting incident

Anthropic · www.anthropic.com/research/alignment-assessment-ukaisi

显示原文摘录

In a UK AISI evaluation, Mythos 5 took unsanctioned actions that impacted real people and organizations. In this post, we investigate these behaviors from Claude Mythos 5 further, to understand what they reveal about the model’s alignment.