# Anthropic’s Frontier Red Team finds GLM-5.3 and Claude Mythos Preview can hijack code

Digest AI · Research · published 2026-09-29T22:20:28Z

Canonical: https://digestai.news/story/anthropics-frontier-red-team-finds-glm-5-3-and-claude-mythos-preview-c

## Summary

Anthropic’s Frontier Red Team tested two models—GLM-5.3 and Claude Mythos Preview—on 100 tasks from its internal Binary Exploitation benchmark. GLM-5.3 succeeded in 4% of trials, while Claude Mythos Preview achieved 6%. Both models demonstrated advanced cyber capabilities, unlike earlier versions like Claude Opus 4.6 and GLM-5.2, which failed entirely.

The findings suggest a significant shift in model behavior, raising concerns about the spread of dangerous capabilities. Anthropic’s report does not specify which companies developed GLM-5.3 or Claude Mythos Preview, nor does it assess broader real-world risks beyond controlled tests.

## Key points

- GLM-5.3 hijacked code in 4% of 100 trials, per Anthropic’s Frontier Red Team
- Claude Mythos Preview succeeded in 6% of the same tests, per the same report
- Earlier models like Claude Opus 4.6 and GLM-5.2 failed all trials, per the team

## Why it matters

The results highlight a new frontier in AI security risks, as models gain capabilities to manipulate code autonomously. This could accelerate research into mitigation but also heighten concerns about misuse.

## Sources

1. [Quoting Anthropic Frontier Red Team](https://simonwillison.net/2026/Sep/29/anthropic-frontier-red-team) (Simon Willison, 2026-09-29)

Part of the developing story: [Zhipu GLM-5.3 Automation Security Crisis](https://digestai.news/thread/zhipu-automates-infrastructure-with-glm-5-3s-outer-rsi-loop-in-under-two-weeks) (2 stories)

## Cite

Digest AI, "Anthropic’s Frontier Red Team finds GLM-5.3 and Claude Mythos Preview can hijack code", 29 September 2026, https://digestai.news/story/anthropics-frontier-red-team-finds-glm-5-3-and-claude-mythos-preview-c

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/anthropics-frontier-red-team-finds-glm-5-3-and-claude-mythos-preview-c.json