EP 63: Eliezer Yudkowsky (AI Safety Expert) Explains How AI Could Destroy Humanity

Eliezer Yudkowsky is a researcher, writer, and advocate for artificial intelligence safety. He is best known for his writings on rationality, cognitive biases, and the development of superintelligence. Yudkowsky has written extensively on the topic of AI safety and has advocated for the development of AI systems that are aligned with human values and interests. Yudkowsky is the co-founder of the Machine Intelligence Research Institute (MIRI), a non-profit organization dedicated to researching the development of safe and beneficial artificial intelligence. He is also a co-founder of the Center for Applied Rationality (CFAR), a non-profit organization focused on teaching rational thinking skills. He is also a frequent author at LessWrong.com as well as Rationality: From AI to Zombies.In this episode, we discuss Eliezer’s concerns with artificial intelligence and his recent conclusion that it will inevitably lead to our demise. He’s a brilliant mind, an interesting person, and genuinely believes all of the stuff he says. So I wanted to have a conversation with him to hear where he is coming from, how he got there, understand AI better, and hopefully help us bridge the divide between the people who think we’re headed off a cliff and the people who think it’s not a big deal.(0:00) Intro(1:18) Welcome Eliezer(6:27) How would you define artificial intelligence?(15:50) What is the purpose of a firm alarm?(19:29) Eliezer’s background(29:28) The Singularity Institute for Artificial Intelligence(33:38) Maybe AI doesn’t end up automatically doing the right thing(45:42) AI Safety Conference(51:15) Disaster Monkeys(1:02:15) Fast takeoff(1:10:29) Loss function(1:15:48) Protein folding(1:24:55) The deadly stuff(1:46:41) Why is it inevitable?(1:54:27) Can’t we let tech develop AI and then fix the problems?(2:02:56) What were the big jumps between GPT3 and GPT4?(2:07:15) “The trajectory of AI is inevitable”(2:28:05) Elon Musk and OpenAI(2:37:41) Sam Altman Interview(2:50:38) The most