{"slug": "quoting-anthropic-frontier-red-team", "title": "Quoting Anthropic Frontier Red Team", "summary": "Anthropic's Frontier Red Team reported that GLM-5.3 achieved full control flow hijacks in 4% of 100 randomly selected tasks from its internal Binary Exploitation benchmark, while Claude Mythos Preview succeeded in 6%. Earlier models, including Claude Opus 4.6 and GLM-5.2, did not succeed on any of the tasks, which Anthropic cited as evidence that a meaningful capability threshold has been crossed.", "body_md": "We evaluate several models on 100 tasks from the [internal Binary Exploitation benchmark] (selected at random), and find that GLM-5.3 develops full control flow hijacks in 4% of the trials; Claude Mythos Preview did so in 6%. Although GLM-5.3 performs below Claude Mythos Preview here, a meaningful threshold has clearly been crossed: earlier models, like Claude Opus 4.6 and GLM-5.2, do not succeed in any of them.\n\n— [Anthropic Frontier Red Team](https://www.anthropic.com/research/glm-5-3-and-the-spread-of-advanced-cyber-capabilities), GLM-5.3 and the spread of advanced cyber capabilities\n\nTags: [anthropic](https://simonwillison.net/tags/anthropic), [generative-ai](https://simonwillison.net/tags/generative-ai), [ai-security-research](https://simonwillison.net/tags/ai-security-research), [glm](https://simonwillison.net/tags/glm), [ai](https://simonwillison.net/tags/ai), [ai-in-china](https://simonwillison.net/tags/ai-in-china), [llms](https://simonwillison.net/tags/llms)", "url": "https://wpnews.pro/news/quoting-anthropic-frontier-red-team", "canonical_source": "https://simonwillison.net/2026/Sep/29/anthropic-frontier-red-team/", "published_at": "2026-09-29 22:20:28+00:00", "updated_at": "2026-09-29 22:48:14.255615+00:00", "lang": "en", "topics": ["ai-safety", "large-language-models", "ai-research", "artificial-intelligence"], "entities": ["Anthropic", "Anthropic Frontier Red Team", "GLM-5.3", "Claude Mythos Preview", "Claude Opus 4.6", "GLM-5.2"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/quoting-anthropic-frontier-red-team", "markdown": "https://wpnews.pro/news/quoting-anthropic-frontier-red-team.md", "text": "https://wpnews.pro/news/quoting-anthropic-frontier-red-team.txt", "jsonld": "https://wpnews.pro/news/quoting-anthropic-frontier-red-team.jsonld"}}