Dane Stuckey (OpenAI CISO) on Prompt Injection Risks for ChatGPT Atlas
Source: simonwillison.net
As always, a big difference between AI systems and a human is that an AI system cannot be held accountable for its actions. I’ll let my trusted friend use my logged-in browser only because there are social consequences if they abuse that trust!
Read Dane Stuckey (OpenAI CISO) on Prompt Injection Risks for ChatGPT Atlas