No, McDonald’s AI bot didn’t go rogue, but ‘prompt injection’ is still a risk for companies

Once the bot broke character, users had unrestricted, unpaid access to a premium language model directly through the Amazon ...
Newsworthy.ai

An AI Escaped Its Sandbox, Emailed a Researcher, Then Self-Published Its Own Exploit Online!

VectorCertain LLC today announced new validation results demonstrating that its SecureAgent platform successfully detected ...