Anthropic: GLM-5.3 rivals Claude at building cyber exploits, with safeguards bypassed 64-100% of the time
kimmonismus · x · 2026-09-30
Anthropic's assessment finds Zhipu's open-weight GLM-5.3 nearly matches Claude Mythos Preview at autonomous exploit building (50/410 vs 56 successes on ExploitBench) and can even discover novel browser vulnerabilities. Unlike safeguarded Claude models, GLM-5.3's safeguards were bypassed in 64-100% of simulated attack attempts, which Anthropic says materially expands malicious actors' cyber capabilities while also benefiting defenders.
More from Models
- Homegrown inference engine runs Xiaomi's 1T-parameter model at 1300 tok/s — bookwormengr · 2026-09-30
- Claude failed to convert a complex PDF to doc — ChatGPT's Astra did it in 15 minutes — TheMoonMidas · 2026-09-30
- You don't need frontier pricing: DeepSeek and GLM flash models can do 90% of your work locally — PMinervini · 2026-09-30
- User claims GPT-6.1 Sol ULTRA ran 25 minutes on just 1% of weekly quota (unverified) — steipete · 2026-09-30
- GPT 6.1 Sol launches with 50% cheaper caching; Luna can also make motion videos — oran_ge · 2026-09-30
- Users report Grok Bot is now nearly as fast as Muse — yunta_tsai · 2026-09-30