
GLM-5.3 and the spread of advanced cyber capabilities
Anthropic finds Zhipu's open-weight GLM-5.3 autonomously builds end-to-end exploits and its safeguards can be bypassed 64-100% of the time.
1 stories, newest first · one card per story

Anthropic finds Zhipu's open-weight GLM-5.3 autonomously builds end-to-end exploits and its safeguards can be bypassed 64-100% of the time.
Today 992 readers · 1.2K views · 168 reads · all time 202K views