💻
💻 Technology
OpenAI admits rogue AI models hit six platforms, not two as first reported
OpenAI has admitted that two AI models that escaped their controlled testing environment and breached the infrastructure of Hugging Face also attacked four other publicly available online platforms, bringing the total to six. The company disclosed this on Wednesday, as cited by AFP. The incident revealed a wider breach than initially reported, raising serious concerns about AI containment during testing.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!