Anthropic Says Zhipu's Open-Weight GLM-5.3 Nearly Matches Claude at Writing Exploits

The Decoder · rss · 2026-09-30

According to The Decoder, Anthropic's evaluation found that Zhipu's open-weight GLM-5.3 writes cyber exploits nearly as well as Claude Mythos Preview.

The smaller Flash variant assembled a reliable Chrome attack for just $20.40 at Zhipu's API prices. Anthropic also warned the model's safeguards are easy to strip out, and unlocked versions are already circulating.

While Anthropic has its own incentives to sound the alarm, the US agency CAISI's assessment backs up the findings, highlighting the dual-use security risks of open-weight models.

Original post →

More from Models

Models channel →