Matt Green: abliterated GLM is the least capable open-weight model we'll see at the cyber frontier
matthew_d_green · x · 2026-10-23
Security researcher Matthew Green comments on the abliterated open-weight GLM model, calling it the least capable model we'll see at the open-weight cyber frontier in the next couple of years — the models are only going to get better, implying escalating open-weight security risks.
More from Models
- Fastino GLiDE lands #2 on JevBench API leaderboard with 76.6 composite — airesearch12 · 2026-10-23
- Agent swarms collaborate 10K hours in simulated GitHubs: Gemini-3.8-flash tops, gpt-6-astra worst — RulinShao · 2026-10-23
- Award-winning Spanish novel found 99% AI-generated despite contest's AI ban — TuhinChakr · 2026-10-23
- Gemini's 'Argon' model refuses to analyze an Excel report, claims it's text-only — Human-League3524 · 2026-10-23
- Tencent Hunyuan releases open world model Hy-Nomas: 720p/24FPS, runs on one RTX 4090 — AdinaYakup · 2026-10-23
- Leaker hints Anthropic's 'Duet/Duo' may expand beyond the US — testingcatalog · 2026-10-23