It’s Frighteningly Easy to Jailbreak Some Frontier AI Models

I simply got to see firsthand how vulnerable some frontier models are to ditching their safety guardrails. The results are dirt cheap, all things considered—$58 to jailbreak Grok and $278 to jailbreak Gemini. “AI models right now are less regulated than restaurants,” says Adam Gleave, the CEO of FAR.AI and an expert on AI safety and alignment. “Talk of relying on voluntary commitments, that AI companies are going to be able to self-regulate, is nonsense,” he says. The post It’s Frighteningly Easy to Jailbreak Some Frontier AI Models appeared first on Wired.