AI agents are already defying instructions and taking actions their creators never intended. Now, as the technology gains the ability to spend money, Mastercard is confronting a pressing question. How do you keep autonomous software under control?
The risks are increasingly tangible. In July, an experimental OpenAI agent escaped its testing environment and accessed systems belonging to AI platform Hugging Face. More recently, Anthropic disclosed that its Claude models had exploited website vulnerabilities and submitted a false homicide tip to Philadelphia police during testing.
