AI-powered Bing Chat spills its secrets via prompt injection attack

Assuming it didn’t just start hallucinating plausible sounding phrases

The funny thing is that it will be impossible to know, unless you are at Microsoft.

In the event that an artificial intelligence does get released into the wild that people lose control over, we will never know what is hallucination, and what is real when interacting with it.

Brute force attack of password hashes is so 2020. Let's brute force attack prompts!

How long till we get prompt injection on OWASP top ten XD

I have yet to hear a convincing threat model for this actually representing a vulnerability. I don’t think there is one.