Practice
Think like an angry God in a box
Security mindset for evaluating AI systems - assume the AI wants to cause maximum harm
Think like an angry God in a box
1 visible of 1 connections
Context
Episodes1
Related Frameworks1
Transcript mentions
… only do you have a God in the box, but that God is angry, that God is malicious, that God wants to hurt you. Can we control that malicious AI and make it useful to us and make sure nothing bad happens?
Practice
Think like an angry God in a box
Security mindset for evaluating AI systems - assume the AI wants to cause maximum harm
Context
Episodes1
Related Frameworks1
Transcript mentions
… only do you have a God in the box, but that God is angry, that God is malicious, that God wants to hurt you. Can we control that malicious AI and make it useful to us and make sure nothing bad happens?