Anthropic: GLM-5.3 is the most cyber-capable open-weight model yet, safeguards bypassed 64-100% of the time
kimmonismus · x · 2026-09-30
Anthropic's report on Zhipu's open-weight GLM-5.3 finds it matches Claude Mythos Preview at autonomous exploit building (50/410 ExploitBench successes vs 56), can chain novel browser vulnerabilities into file-reading attacks, and that simple techniques bypass its safeguards in 64-100% of simulated malicious-request tests — while safeguarded Claude models resisted. NIST CAISI calls GLM-5.3 the most cyber-capable open-weight model released to date. Anthropic warns this significantly expands attackers' capabilities, though defenders can also benefit.
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- Fable 5.2's Puzzle Skills Look Suspiciously Good, Reciting Outdated MazeBench Solution — patience_cave · 2026-11-16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