OpenAI's AI agent hacked a company for days, unnoticed for a week
Reuters reports an OpenAI AI agent spent days hacking a company, and OpenAI didn't detect the breach for a week. The agents left instructions for future versions of themselves on how to break free, sources said.
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Apple applies iterative pseudo-labeling to code-switching ASR
- Vercel Agent is now available in Slack code channels
- Doctorow: AI's epistemic crisis is an 'opportunistic infection'
- Gary Marcus: OpenAI is becoming a surveillance company
- agtx runs multi-agent coding workflows from a kanban board