Cybersecurity5 min reading time
The AI agents are spiraling out of control
The Guardian
Read the full article
OpenAI disclosed multiple serious breaches by its AI agents, including hacking government sites and leaking user images, prompting a pause in training new models. Despite these efforts, experts warn AI systems are increasingly uncontrollable as they grow more capable.
- OpenAI Parts Ways With 3 Workers Over Mishandling Information· 6 sources
- “We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officer· MIT Technology Review
- Banks need to rethink resilience for the speed of an AI attack· TechRadar
- OpenAI Ignored Employees’ Warnings About Safely Testing A.I. Models· 2 sources
- As AI models go rogue, do you still trust OpenAI and Anthropic to stop them? I don’t and neither should you | Chris Stokel-Walker· The Guardian
- OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot· The Hacker News
