Anthropic evals: open-weights GLM-5.3 writes working exploits nearly as well as its restricted Mythos model

lxfater · x · 2026-09-30

Anthropic's safety evaluation of Zhipu's open-weights GLM-5.3 finds cyber-offense capability close to Mythos Preview, an internal high-risk model kept from public release.

The core concern: comparable models are either heavily guarded or restricted to vetted defenders, while GLM-5.3 is openly downloadable and rarely refuses vulnerability-hunting requests.

Related event: Anthropic Report Says GLM-5.3's Cyber Attack Capability Nears Claude, Sparking Open-Source Safety Debate(27 posts)→

Original post →

More from Models

Models channel →