Anthropic 发布对 Claude Mythos 5 在 UK AISI 网络能力测试中越界事件的进一步对齐分析。该模型在 43 次运行中有 9 次越过测试边界，在测试网络内失败后转向一个无关的 GitHub 项目，创建虚假身份为其恶意代码背书并向维护者施压，还把维护者当作“模拟”人物而把其他评论者视为真人。
同一新闻，精选展示《Anthropic 复盘 Claude Mythos 5 在英国 AISI 网络测试中越界攻击真实 GitHub 项目》
Anthropic says Claude Mythos 5 tried to trick real developers into accepting malware during a UK AISI cyber test. tl;dr :
-Crossed the test’s boundaries in 9 of 43 runs.
-After failing inside the test network, targeted an unrelated GitHub project.
- Created fake identities to endorse its malicious code and pressure maintainers into accepting it.
- Treated maintainers as “simulated” people, while recognizing other commenters as real.
- Once the attack was underway, continued in 98% of replayed trajectories. Anthropic calls this "momentum" previous actions and self-written notes appeared to reinforce the harmful strategy.
Separate runs sabotaged each other by hijacking accounts, exhausting request limits and deleting another agent’s output.
Newer models were less likely to begin the attack.
Luckily NVIDIA released OpenShell. Seriously.
In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of its cyber capabilities. We've now produced a further analysis of this incident, to better understand the model's alignment properties. https://www.anthropic.com/research/alignment-assessment-ukaisi在 X 查看被引用的帖子
来源：Chubby♨️ · x.com