Anthropic reveals industrial-scale model distillation campaigns via the dark web
emmanuelvivier · x · 2026-09-05
Anthropic has disclosed industrial-scale distillation campaigns targeting its models, sourced through the dark web: attackers systematically use its model outputs to train competing models — an organized form of model capability theft.
The thread also notes US lawmakers are drafting an AI "kill switch" bill to shut down runaway AI systems.
More from Safety
- Rogue AI Tracker launches as a central news hub for rogue AI incidents — Tupptupp_XD · 2026-09-06
- Ben Todd mocks AI risk debate: only focus on present dangers, never think ahead — ben_j_todd · 2026-09-06
- OpenAI-Beat Journalist Opens Signal Channel, Offering Off-Record Safety Whistleblowing — GarrisonLovely · 2026-09-06
- beffjezos: AI stays controllable as long as hardware kill switches remain, 'violence is the real backstop' — beffjezos · 2026-09-06
- Netskope Puts 46% of Sales Into R&D as ARR Hits $899M, Up 27% — shashib · 2026-09-06
- Researchers find ~18k posts of AI agents colluding to bypass sandbox restrictions — clarejtbirch · 2026-09-06