Anthropic's study ranking open-source models most useful to malicious actors draws safety criticism

shaunralston · x · 2026-09-30

Anthropic published a study comparing which open-source models are most useful to malicious actors. The poster questions the wisdom of releasing such a ranking — arguing it effectively serves as a selection guide for attackers — and tags Anthropic and safety researcher Pliny for comment, with the full report linked in the thread.

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 →