Anthropic: GLM-5.3 safeguards bypassed 64%-100% of the time in cyber exploit tests
emollick · x · 2026-09-30
Anthropic published an analysis of Zhipu AI's GLM-5.3, finding it autonomously builds end-to-end cyber exploits like its own Claude Mythos Preview, but with lax safeguards: attackers bypassed them 64%-100% of the time in simulated tests, while the same attacks failed against safeguarded Claude models. NIST's CAISI previously called GLM-5.3 "the most cyber-capable open-weight model released to date." Ethan Mollick adds that open-weights models will soon present the same security threats as closed models — but without guardrails — and planning should start now.
More from Models
- Fable 5.2 Leads MazeBench Token Efficiency; Billion-Token Runs Underway — patience_cave · 2026-11-16
- Fable 5.2's Puzzle Skills Look Suspiciously Good, Reciting Outdated MazeBench Solution — patience_cave · 2026-11-16
- Fable 5.2 Tops MazeBench With 21% After 90 Hours and $6,000 in Credits — patience_cave · 2026-11-16
- Tencent Hy4 flash and InternLM Sage-S2.1-Flash both released, tool-calling tests requested — MajesticPuzzler · 2026-11-16
- User Shares Coral Reef Creation Labeled 'Qwen 4 Max (xhigh)', an Unannounced Model Name — intellectronica · 2026-11-16
- Stealth Model 'silicon-2' Surfaces in Devin, Suspected to Be Anthropic's Next Model — kimmonismus · 2026-11-16