Matthew Green questions why a compromised inference provider served an abliterated model
matthew_d_green · x · 2026-11-20
Security researcher Matthew Green asks why anyone would compromise an inference provider only to substitute an 'abliterated' (safety-guardrail-removed) model.
A reply speculates the attacker wanted the abliterated model for themselves and accidentally pushed it to Prime Intellect's public inference endpoint. Unconfirmed; details still unclear.
More from Models
- GPT 6.2 Sol remains #1 for computer/browser use, says Matthew Berman — MatthewBerman · 2026-11-20
- Microsoft's MAI models have been front-page on Hacker News since Ignite debut — marlene_zw · 2026-11-20
- Gemini 4 Carbon tops graduate-level physics benchmark but loses on agentic tasks — ArtificialAnlys · 2026-11-20
- Neon and Hydrogen own every Pareto frontier in Gemini 4 lineup, from $0.29 to $6.44 per task — ArtificialAnlys · 2026-11-20
- Gemini 4 lineup pricing revealed: Carbon $4/$20, Neon $3/$15, Hydrogen $1.50/$7.50 — ArtificialAnlys · 2026-11-20
- Google opens Project Genie 4 waitlist access to Google AI Pro subscribers — testingcatalog · 2026-11-20