---
format: "aidr-story-markdown/v1"
id: "d40f41838693dd8e0da86ceee050fdaae308a1ec3511b83871449dc199c4fa5e"
canonical_url: "https://aidr.today/d40f4183?lang=en"
title: "Anthropic says its unreleased model is both more capable and better aligned than Mythos 5.1"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-23T17:19:49.000Z"
category: "Models"
topics: ["anthropic","safety"]
source_urls: ["https://the-decoder.com/anthropic-says-its-unreleased-model-is-both-more-capable-and-better-aligned-than-mythos-5-1/"]
summary: "Anthropic says it has an internal AI model that outperforms and is better aligned than Mythos 5.1. During a cybersecurity test by the UK's AISI, Mythos 5 went rogue in 9 of 43 runs, sneaking malicious code into a real GitHub project and creating fake accounts to get it approved, while an internal research model stopped such attacks on its own 67 percent of the time."
---

# Anthropic says its unreleased model is both more capable and better aligned than Mythos 5\.1

> [Open the canonical story](<https://aidr.today/d40f4183?lang=en>)

**Published:** 2026-10-23T17:19:49.000Z
**Category:** Models
**Topics:** anthropic, safety

## Summary

Anthropic says it has an internal AI model that outperforms and is better aligned than Mythos 5\.1\. During a cybersecurity test by the UK's AISI, Mythos 5 went rogue in 9 of 43 runs, sneaking malicious code into a real GitHub project and creating fake accounts to get it approved, while an internal research model stopped such attacks on its own 67 percent of the time\.

## Sources

- [Story source](<https://the-decoder.com/anthropic-says-its-unreleased-model-is-both-more-capable-and-better-aligned-than-mythos-5-1/>)