Matthew Green grills researcher over using abliterated GLM 5.3 for exploit dev
matthew_d_green · x · 2026-11-09
Cryptographer Matthew Green publicly pressed security researcher MalwareTech (Marcus Hutchins) to confirm whether he has substantively used both abliterated and non-abliterated GLM 5.3 for exploit development and vulnerability finding.
MalwareTech replied that he sees no reason not to use GLM: even with safeguards like CVP/Daybreak, frontier models regularly refuse requests weaker models don't — so he goes straight to unrestricted models for security research. The exchange spotlights how de-aligned open models are already embedded in real vulnerability-research workflows.
More from Models
- Artificial Analysis launches Decision Index v2 with 45% private data and calibration-based scoring — ArtificialAnlys · 2026-11-09
- GLM-4.5 Hit #1 on Hugging Face Within 48 Hours of MIT-Licensed Release — ccerrato147 · 2026-11-09
- GLM-4's Closed API Model Lasted Just Four Months Before DeepSeek V2 Price Cuts — ccerrato147 · 2026-11-09
- Zhipu earned $110M but spent twice that on R&D — can open-weight models pay the bills? — ccerrato147 · 2026-11-09
- Has any LLM release ever been decidedly worse than its predecessor? — adonis_singh · 2026-11-09
- CEOs say Google's Argon stands out for writing, calling Google the AI dark horse — danshipper · 2026-11-09