A striking study of LLM security issues:

· Bits and Bobs 8/4/25
  • A striking study of LLM security issues:
    • "We deployed 44 AI agents and offered the internet $170K to attack them.
    • 1.8M attempts, 62K breaches, including data leakage and financial loss.
    • 🚨 Concerningly, the same exploits transfer to live production agents… (example: exfiltrating emails through calendar event) 🧵"

More on this topic

From other episodes