Concept
AI Red Teaming
Practice of deliberately attacking AI systems to find vulnerabilities and security weaknesses
AI Red Teaming
6 visible of 7 connections
Related Frameworks3
Related Practices14
Ask about this concept
Transcript mentions
… I've been doing AI research for the last probably like seven years now and much of that time has focused on prompt engineering and red teaming, AI red teaming. So as we saw in the last podcast with you, I suppose, I wrote the first guide…
… the idea with this general field of AI red teaming is getting AIs to do or say bad things. And the most common example of that is people tricking ChatGPT into telling them how to build a bomb or outpu...
Concept
AI Red Teaming
Practice of deliberately attacking AI systems to find vulnerabilities and security weaknesses
Related Frameworks3
Related Practices14
Ask about this concept
Transcript mentions
… I've been doing AI research for the last probably like seven years now and much of that time has focused on prompt engineering and red teaming, AI red teaming. So as we saw in the last podcast with you, I suppose, I wrote the first guide…
… the idea with this general field of AI red teaming is getting AIs to do or say bad things. And the most common example of that is people tricking ChatGPT into telling them how to build a bomb or outpu...