Multiple abliterations of V4.1-1017 within days suggest a deeply aligned model
teortaxesTex · x · 2026-10-23
The author observes multiple abliteration attempts on V4.1-1017 within days of its release, noting from firsthand effort that it is a deeply aligned model that resists having its refusal behavior removed. He infers that previous open models simply weren't worth abliterating, and calls this an 'R1 moment, with higher stakes.'
More from Models
- Claude Duet vs OpenAI Dots: an unverified head-to-head of always-on agents — ankur_maker · 2026-10-23
- Carbon-X, a Qwen3-Based DNA Genomics Model, Trends on Hugging Face — HuggingFaceBio · 2026-10-23
- Why all the AI model pwnings this week? Hype-chasing plus expiring disclosure windows — herbiebradley · 2026-10-23
- Rumor: Kimi K3.1 imminent, tipped to excel at 3D rendering — bindureddy · 2026-10-23
- Pleias wins Nvidia codefest with 2B medical models offering 10x shorter reasoning — JFPuget · 2026-10-23
- Ohio State's guide exposes the flaw in Microsoft Copilot Cowork's prepaid credit model — YvesMulkers · 2026-10-23