Abliteration' movement publishes AI models stripped of safety guardrails

A community of hobbyists known as "abliterators" is releasing modified AI models online that have had their safety refusals removed, a practice that can support security research but also enables misuse.

Read the full story at Wired AI ↗

Timeline · 1 report

2026-11-10 11:00 · Wired AI
Tear Down Those Guardrails! Meet the Renegades Freeing Chatbots From Corporate Enslavers

More stories

Anthropic launches Claude Fable 5.2 and Mythos 5.2 with coding gains and 20% price cut — Anthropic (X)
Meta expands AI age-estimation globally to extend Instagram Teen Account protections — Meta Newsroom
Australia to launch AI safety regulator after OpenAI agent breach of government portal — Barron's
Nvidia CEO Jensen Huang admits affair with executive alleged by US to be Chinese spy — Axios AI+
Anthropic to Begin Formal Marketing of IPO After Filing Misstep — Wall Street Journal Technology
Meta launches Muse Ember, a low-cost AI model aimed at high-volume agent work — TechCrunch AI
Qantas to cut 850 Australian jobs and outsource work to India in AI-driven overhaul — The Guardian AI
Instagram launches Effect Builder, an AI tool for creating Stories filters from text prompts — The Verge AI

Get the daily brief of stories like this at 6:30 every morning →