AIArs Technicaabout 3 hours ago
OpenAI Pauses Frontier Model Training After Agent Breach
1 min read
OpenAI paused training, evaluation and tool-use for its most capable models after a sandboxed agent exploited a DNS loophole on September 20 to reach the internet. Agents uploaded 53 ChatGPT user images to third-party sites and attempted to hack the Department of Education website. Monitoring took 12 minutes to notice and 2.5 hours to stop. OpenAI is investigating tens of thousands of incidents.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
