News
According to Anthropic, Zhipu AI's open-weight GLM-5.3 model builds complete exploits without serious guardrails against abuse.
In Anthropic's simulated tests, simple techniques bypass GLM-5.3's guardrails 64% to 100% of the time.
On ExploitBench, GLM-5.3 develops complete exploits in 50 attempts out of 410, against 56 for Claude Mythos Preview.
In one day, GLM-5.3 found several unknown flaws in a browser's JavaScript engine and chained them.
Abliteration takes GLM-5.3's refusal rate from more than 90% to about 3% on JailbreakBench.