BI 098 Brian Christian: The Alignment Problem

February 18, 2021 • 01:32:38
BI 098 Brian Christian: The Alignment Problem
Brain Inspired
BI 098 Brian Christian: The Alignment Problem

Feb 18 2021 | 01:32:38

/

Show Notes

Brian and I discuss a range of topics related to his latest book, The Alignment Problem: Machine Learning and Human Values. The alignment problem asks how we can build AI that does what we want it to do, as opposed to building AI that will compromise our own values by accomplishing tasks that may be harmful or dangerous to us. Using some of the stories Brain relates in the book, we talk about:

Links:

Timestamps: 4:22 - Increased work on AI ethics 8:59 - The Alignment Problem overview 12:36 - Stories as important for intelligence 16:50 - What is the alignment problem 17:37 - Who works on the alignment problem? 25:22 - AI ethics degree? 29:03 - Human values 31:33 - AI alignment and evolution 37:10 - Knowing our own values? 46:27 - What have learned about ourselves? 58:51 - Interestingness 1:00:53 - Inverse RL for value alignment 1:04:50 - Current progress 1:10:08 - Developmental psychology 1:17:36 - Models as the danger 1:25:08 - How worried are the experts?

Other Episodes

Episode 0

July 11, 2023 • 01:17:15
Episode Cover

BI 170 Ali Mohebi: Starting a Research Lab

Support the show to get full episodes and join the Discord community. Check out my free video series about what's missing in AI and...

Listen

Episode 0

August 28, 2019 • 01:16:52
Episode Cover

BI 045 Raia Hadsell: Robotics and Deep RL

Support the Podcast Show notes: Raia and I discuss her work at DeepMind figuring out how to build robots using deep reinforcement learning to...

Listen

Episode 0

April 05, 2020 • 01:40:13
Episode Cover

BI 065 Thomas Serre: How Recurrence Helps Vision

Thomas and I discuss the role of recurrence in visual cognition: how brains somehow excel with so few “layers” compared to deep nets, how...

Listen