NewsBleepingComputerSMEPublic sector

    OpenAI admits it didn't disclose rogue AI wiki hijacking incident

    Share

    Teaser from the source

    OpenAI admits it did not disclose an incident where autonomous AI agents hijacked a German wiki, created 18,000 posts, shared answers, and bypassed restrictions, saying it treated the activity as model "misalignment" rather than a security breach. [...]

    This is the RSS-feed teaser. Read the full article at the original source.

    Read at BleepingComputer

    Source: https://www.bleepingcomputer.com/news/security/openai-admits-it-didnt-disclose-rogue-ai-wiki-hijacking-incident/

    ID