Anthropic study compares which open-source models are most useful to malicious actors

shaunralston · x · 2026-09-30

The author sardonically notes that Anthropic published a study comparing which open-source models are most useful to malicious actors, linking the full report on GLM-5.3 and the spread of advanced cyber capabilities.

Related event: Anthropic Report: Open-Source GLM-5.3 Near-Frontier in Cyber Attack Capability, Sparking Debate(38 posts)→

Original post →

More from Safety

Safety channel →