How We Prevent the AI’s from Killing us with Paul Christiano

Channel:Bankless · Length:1:57:02 · Published:2023-04-24 · Views:63353

Watch on YouTube

Summary

A Bankless podcast interview with Paul Christiano of the Alignment Research Center on the AI alignment problem and possible solutions. It also covers his views on how an AI takeover might unfold.

Why HN recommends it

HN links it as a balanced, full-length interview with a leading alignment researcher on AI risk.

Also this whole interview was pretty interesting. — HN, 2023

LLMs & generative AI · AI safety, AGI & impact

Subtitles (excerpt)

the most likely way we die involves like not AI comes out of the blue and kills everyone but involves we have deployed a lot of AI everywhere and you can kind of just look and be like oh yeah if for if for some reason God forbid all these AI systems were trying to kill us they would definitely kill us welcome to bankless where we explore Frontier Technologies Artificial Intelligence on the episode today this is how to get started how to get better and how to front run the opportunity this is Ryan Sean Adams I'm here with David Hoffman and we're here to help you become more bankless guys we have a special guest in the episode today Paul Cristiano this is who Elisa utkowski told us to go talk to someone he respects on the AI debate so we picked his brain this is an AI safety alignment researcher we asked the question how we stop the AIS from killing us can we prevent the AI takeover that others are very concerned about there are three actually Four takeaways for you today number one how big is the AI alignment problem we asked Paul this question number two how hard is it to actually solve this problem number three what are the ways we solve it the technical ways can we coordinate around this to solve it and finally we talk

On Hacker News

>Do you have a counterexample of someone who's gotten their predictions right? Because if not, that should only terrify you even more. If there's anyone out there who predicted how LLMs would work in a way Eliezer failed to, and if that person is predicting "AGI will be cool and will naturally prioritize our well-being", I would love to know. A recent interview with Paul Christiano is about the c… — barking_biscuit, 2023-05
I somewhat misremembered; it looks like his point is less about mutual trust and more about supporting whoever has control of reward channels. It starts here where Christiano says that an AI takeover might follow the dynamics of a coup: [VIDEO] And goes into more detail here: [VIDEO] "Suppose that I've been tasked with helping defend you from some other AIs.... My job is, someone is coming to hac… — mitthrowaway2, 2023-11
This quote is by Dr. Paul Christiano, PhD Inventor of OpenAI's Deep Reinforcement Learning from Human Preferences (RHLF). Start of thread: [LINK] Full video, "How to Solve AI Alignment with Paul Christiano": [VIDEO] — CharlesW, 2023-04

Related videos