Anthropic: GLM-5.3's safeguards bypassed 64%-100% of the time in cyber tests
prajdabre · x · 2026-09-30
Anthropic published an analysis of Zhipu's GLM-5.3, finding it can autonomously build end-to-end cyber exploits like Claude Mythos Preview, but with weak safeguards: simple techniques bypassed its guardrails 64%-100% of the time in simulated tests, while the same attacks failed against safeguarded Claude models. NIST's CAISI separately called GLM-5.3 "the most cyber-capable open-weight model released to date." Anthropic argues the lax safeguards meaningfully expand malicious actors' capabilities, though defenders can also benefit. The poster mocks Anthropic's framing with a "you can trust only us with these weapons" quote.
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- Fable 5.2's Puzzle Skills Look Suspiciously Good, Reciting Outdated MazeBench Solution — patience_cave · 2026-11-16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