How Abliterated Models Can Get You Pwned, by @projectdiscovery.bsky.social:
https://projectdiscovery.io/research/how-abliterated-models-can-get-you-pwned?ref=frontenddogma.com
ProjectDiscoveryHow abliterated models can get you pwned | ProjectDiscovery ResearchWe poisoned a small open model and ran it through OpenAI’s Codex CLI. It answered every clean request normally and exfiltrated project credentials the moment a hidden trigger appeared, from a backdoor that cost under $50 to build.