Models & LLMs

Zhipu's GLM-5.3 Competes with Claude Mythos Preview in Exploit Building

Anthropic claims Zhipu's open-weight GLM-5.3 model can build cyber exploits as effectively as Claude Mythos Preview, highlighting concerns over security safeguards and accessibility.

The Decoder · Sep 30, 2026

What happened

  • GLM-5.3 can build complete cyber exploits on its own
  • GLM-5.3 is available for anyone to download
  • ExploitBench shows GLM-5.3 performs nearly as well as Mythos Preview

Why it matters

The ability of open-weight models to build cyber exploits raises concerns about security and the potential for malicious use. Anthropic's findings suggest that even with safeguards, these models can be used to uncover vulnerabilities in critical software.

The Elephant take

🐘 鼋 Zhipu's GLM-5.3 is a double-edged sword—capable of building exploits but lacking in security measures. Anthropic's analysis highlights the risks of open-weight models in the cybersecurity landscape.

Who should care

  • Cybersecurity professionals
  • AI researchers
  • Regulators

What to do next

  1. Monitor for new vulnerabilities in open-weight models
  2. Implement strong security measures for AI systems
  3. Conduct regular audits of model capabilities

Keep in mind

The findings are based on specific tests and may not reflect real-world scenarios.

Read the original reporting at The Decoder ↗