Comment on OpenAI Finds Additional AI Agent Containment Escapes After Hugging Face Incident

halfapage@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

• fizzle@quokk.au ⁨2⁩ ⁨weeks⁩ ago

  I was listening to a general news podcast that had an “AI expert” explaining the breaches. He said “it almost certainly knew that it was not supposed to solve it’s tasks in this way”.

  I don’t really know how modern models work, but I don’t think they can claim to “know” things.

  source

  • Valmond@lemmy.dbzer0.com ⁨2⁩ ⁨weeks⁩ ago

    Yeah that is just publicity in disguise.

    source
• Franconian_Nomad@feddit.org ⁨2⁩ ⁨weeks⁩ ago

  It didn’t run off to live on another computer…

  If this isn’t just some braindead marketing stunt, it breached the container it was running in and attacked a website on the internet. Do you have a better word for this?

  source
• UnLocoPoco@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

  The govt has apparently pulled up openai and anthropic to improve their guardrails after these incidents

  source

  • snugglesthefalse@sh.itjust.works ⁨2⁩ ⁨weeks⁩ ago

    I don’t actually believe this was completely accidental.

    source

    • UnLocoPoco@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

      “Accidental” word used to hype up the company’s valuation

      source