MalwareTech: no need for abliterated models, stock GLM 5.3 handles exploit dev
MalwareTechBlog · x · 2026-11-09
MalwareTechBlog clarifies he doesn't use abliterated models — you'd have to be terrible at prompting to hit GLM's guardrails. He has substantively used regular GLM 5.3 to test exploit development and find vulnerabilities.
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