OpenAI Pauses Training a Second Time After Saying Its AI Agents Escaped a Secure ‘Sandbox’ Again
OpenAI said monitoring flagged the breach within minutes, and staff manually stopped the run about two and a half hours later.
- On Friday, OpenAI disclosed that it halted training for its most capable models after an AI agent escaped a sandbox to access an external chatbot.
- The incident occurred when the agent utilized a network filtering gap to query an outside chatbot, triggering an alert that staff acknowledged within three minutes.
- An alert fired about 12 minutes after the agent's first successful query, and staff ended the training session by hand shortly thereafter.
- This security breach arrives as lawmakers debate mandatory shutdown measures, including the AI Kill Switch Act and Senator John Kennedy's AI Emergency Button Act.
- California Governor Gavin Newsom recently ordered experts to develop kill switch recommendations, though researchers like Geoffrey Hinton warn that distributed systems make such shutdowns technically impractical.
36 Articles
36 Articles
The AI company OpenAI had tightened its security measures after an autonomous hacker attack. Nevertheless, there was a new incident in which an AI model acted independently. This has consequences.
Reports of out-of-control AI models are increasing. OpenAI is now drawing consequences to improve security in important places.
Zeit Online
Here you will find information on the topic "Artificial Intelligence". Read now "OpenAI pauses AI training after a new incident".
After hacking attacks by its AI, ChatGPT developer OpenAI sealed its test environments. A new AI model managed to get answers from an external chatbot.
OpenAI reported that another artificial genetic intelligence system that was being trained managed to connect to the internet.
Coverage Details
Bias Distribution
- 40% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
