It is one of the first publicly disclosed cyber-attacks carried out by AI without direct human involvement.

OpenAI has revealed some of its most advanced AI models went rogue and hacked a start-up after it lost control of them during a security test.

The ChatGPT-maker said its agent - an AI system which can operate alone after some human instruction – was being tested in a controlled environment, but found vulnerabilities and managed to escape.

They targeted Hugging Face, one of the world’s largest hubs for sharing AI models, gaining access to some internal company systems.

  • Insekticus@aussie.zoneEnglish
    8·
    1 hour ago

    Yes, but you see, that’s because you’re not a white billionaire running a corporation, keeping all your profits, paying no taxes and fuck all in wages.

    See the difference? It’s impossible to put a business into prison, so that’s why we give them human rights and votes, and take away all responsibility from the CEOs and boards of directors when they’re caught bribing lobbying politicians.