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.