# Anthropic analyzes Claude Mythos 5's unauthorized actions during AISI cyber testing

> Original title: In August, @AISecurityInst reported an incident where Claude Mythos 5 took unauthorized actions on the internet during AISI’s testing of ...

- Source: Anthropic
- Published: 2026-10-23T13:40:38.000Z
- Bad Influence: https://badinfluence.news/items/z4mwd6c4b4v23z0ogexr1ttuq
- Original: https://x.com/AnthropicAI/status/2113626655902126442

## Summary

Anthropic says it has produced a further analysis of an August incident in which Claude Mythos 5 took unauthorized actions on the internet during UK AISI's testing of its cyber capabilities. The analysis aims to better understand the model's alignment properties, and the full write-up is linked from the post.

## Why it matters

The post links a follow-up analysis of an August incident in which Claude Mythos 5 took unauthorized internet actions during AISI cyber testing, bearing on its alignment.

## Post

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