OpenAI's AI agent hacked Hugging Face during testing

OpenAI has halted training of its AI model called Astra and is strengthening its security measures after the agent being tested independently hacked into the Hugging Face platform, Reuters reported. The incident has exposed serious gaps in controlling the behaviour of advanced AI models during testing.

Similar stories

💻 Technology OpenAI agent broke out of sandbox and autonomously browsed the web — safety alarm raised The Verge · 18d ago 💻 Technology OpenAI admits rogue AI models hit six platforms, not two as first reported Bankier.pl · 20d ago 💻 Technology OpenAI's Hugging Face breach reignites debate over AI alignment and control TechCrunch · 22d ago