Anthropic Warns China's GLM-5.3 Builds Exploits Like Mythos
Anthropic's Frontier Red Team published an analysis warning that Z.ai's open-weight model GLM-5.3 can autonomously build full cyber exploits, comparable to its restricted Claude Mythos Preview but without meaningful safeguards. In tests, GLM-5.3 produced 50 successful exploits for known Chrome V8 vulnerabilities out of 410 attempts (close to Mythos's 56), and discovered multiple unknown vulnerabilities in a common browser within a day, chaining them into a working exploit. Anthropic notes that safeguards can be bypassed in 64-100% of cases with simple tricks, and removing them costs only about $4,400. The US NIST's CAISI assessed GLM-5.3 as the most cyber-capable open-weight model to date, though it lags US frontier models by about four months. Z.ai, listed in Hong Kong since January, has seen its market value drop to about $40 billion from $120 billion in June. Critics question Anthropic's commercial motives and highlight defender benefits.
- •Anthropic's Frontier Red Team warned that Z.ai's open-weight GLM-5.3 can autonomously build complete cyberattacks, comparable to Claude Mythos Preview but without safeguards.
- •In tests, GLM-5.3 achieved 50 successful exploits for Chrome V8 vulnerabilities out of 410 attempts, close to Claude Mythos's 56.
- •GLM-5.3 discovered several unknown vulnerabilities in a common browser within about a day and combined them into a working exploit.