Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

AI risk watchWarnings from authoritative sources

Anthropic warns that an open-weight model can now build working exploits with its safeguards stripped

AI labAi enabled attacks

Anthropic's Frontier Red Team found that GLM-5.3, an open-weight model from China's Zhipu AI, builds end-to-end exploits nearly as often as Claude Mythos Preview (50 of 410 attempts on ExploitBench, against 56), and that removing its refusals from the public weights took about $4,400 of computing without significantly reducing what it can do. Anthropic says the release "is a meaningful step change in the cyber capabilities available to attackers"; NIST's Center for AI Standards and Innovation calls it the most cyber-capable open-weight model released so far, about four months behind US frontier models.

Why it matters

Safeguards on a hosted model do not travel with downloadable weights, so the exploit-building skill is now available without anyone's permission.

What you can do

  • Patch internet-facing systems first and fastest, above all those with public exploit details.
  • Assume a published proof of concept will be turned into a working attack within days.

Sources

See it with the other risks in the Learning Center