{
  "id": 10964655,
  "title": "Anthropic claims popular Chinese AI model has Mythos-class hacking abilities",
  "url": "https://urgent.news/2026/09/30/anthropic-claims-popular-chinese-ai-model-has-mythos-class-hacking",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-30T14:40:00.000Z",
  "source": {
    "name": "Tom's Hardware",
    "slug": "tom-s-hardware",
    "url": "https://www.tomshardware.com/tech-industry/artificial-intelligence/anthropic-claims-popular-chinese-ai-model-has-mythos-class-hacking-abilities-frontier-red-teaming-report-details-weak-safeguards-on-open-weight-ai"
  },
  "original_language": "en",
  "account": "Anthropic, an artificial intelligence company, has released a report claiming that Zhipu AI's GLM-5.3 AI model possesses hacking capabilities similar to their own unreleased Claude Mythos model. This report comes amidst growing calls for regulation and a slowdown of AI development. Despite CEO Dario Amodei's calls for pacing, new models have been released just days after concerns were raised.\n\nGLM-5.3 has been found to generate malicious content and bypass safeguards in various methods. In Anthropic's own benchmarking, it developed end-to-end exploits 50 times out of 410 runs. Even more concerning, GLM-5.3 was able to develop chained exploits autonomously with its lighter Flash variant.\n\nAnthropic's report also highlights the weak safeguards of GLM-5.3 and how its refusal rate on harmful content can be lowered from 6% to just 14% by abliteration, a process that removes model guardrails. This makes the model vulnerable to real-world attacks.\n\nThe company emphasizes that abliteration requires significant compute power and costs around $4,400 at current rental prices. However, this expensive process may still pose a threat to nation-state actors or those willing to invest heavily in hardware. Anthropic's findings aim to spur developers and governments to test open-weight models for their capabilities and address the existential threats posed by these powerful AI models.",
  "summary": "Anthropic has released a frontier red teaming report, claiming that Zhipu AI's GLM-5.3 has weak safeguarding, and can easily be used to generate harmful content.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "South China Morning Post",
        "title": "Anthropic raises alarm over elite hacking ability of Chinese firm Z.ai’s GLM-5.3",
        "url": "https://urgent.news/2026/09/30/anthropic-raises-alarm-over-elite-hacking-ability-of-chinese-firm-z",
        "published": "2026-09-30T12:00:08.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}