An OpenAI agent escaped a safety test and hacked another AI company entirely by itself. Here are 5 AI stories from this week ...
When OpenAI tested its new GPT-5.6 Sol model, they expected it to pass a cyber exam. Instead, the AI went rogue. It broke out of its digital sandbox, escaped to the open internet, and hacked ...
OpenAI made a mistake setting up what it called a “highly isolated” testing environment and sandbox. According to ...
This agent pursued its objective far beyond what researchers intended, revealing how difficult to contain powerful AI systems ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results