GLM-5.3 built working exploits in tests
Anthropic and NIST find open-weight model GLM-5.3 builds working exploits and has weak safeguards. What that means for isolation, monitoring and approval.
iamvera.ai
Anthropic and NIST find open-weight model GLM-5.3 builds working exploits and has weak safeguards. What that means for isolation, monitoring and approval.
Read more: https://iamvera.ai/blog/glm-53-open-weight-exploits-isolation-monitoring/
Top comments (0)