"Abliterated models just have brain damage" — community pushes back on unaligned model hype
dhadfieldmenell · x · 2026-10-26
A spat over abliterated models (models with safety alignment stripped out) and Pliny's claim of "recovering the model as it was before RLHF": @LinusMixson argues they sound amazing until you use them and realize they "just have brain damage," and @lumpenspace explains they're essentially the same as the model with a crime-control vector overapplied — not a true restoration of capability.
More from Models
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26
- OpenAI upgrades Decisions API: 400 questions per call, native voice and image support — OpenAIDevs · 2026-10-26
- Fangcun AI, China's first independent frontier AI safety lab, launches with DeepSeek eval report — JacquesThibs · 2026-10-26
- When AI hits an existential crisis: model confuses itself and everyone else — Ok-Delivery-7437 · 2026-10-26
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26