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.

Original post →

More from Models

Models channel →