Chapter
Making Machines Adopt Human Goals
55:37 - 1:03:41 (08:04)
The trust between humans and machines can be improved by making computations more understandable, which involves challenges in transforming intelligent computations. This is important for ensuring that machines adopt and retain human goals.
Clips
The speaker believes that in order to ensure that machines adopt and retain human goals, trust should be based on things that humans can understand and improve upon, preferably through the use of mathematical proofs, and discusses the challenges involved in transforming intelligent computations into ones that are equally intelligent.
55:37 - 1:00:21 (04:43)
Summary
The speaker believes that in order to ensure that machines adopt and retain human goals, trust should be based on things that humans can understand and improve upon, preferably through the use of mathematical proofs, and discusses the challenges involved in transforming intelligent computations into ones that are equally intelligent. The talk touches on the current state of cybersecurity and its vulnerabilities.
ChapterMaking Machines Adopt Human Goals
EpisodeMax Tegmark: Life 3.0
PodcastLex Fridman Podcast
The higher level structure of the brain's network matters more than the individual neurons present.
1:00:21 - 1:01:48 (01:27)
Summary
The higher level structure of the brain's network matters more than the individual neurons present. It is possible to understand how to build AGI before fully comprehending the workings of the human brain.
ChapterMaking Machines Adopt Human Goals
EpisodeMax Tegmark: Life 3.0
PodcastLex Fridman Podcast
A physicist explains the mathematical relationship between artificial neural networks and physics, and how the number of possible problems that we care about in physics is an infinitesimal fraction of all possible problems that can be posed.
1:01:48 - 1:03:41 (01:53)
Summary
A physicist explains the mathematical relationship between artificial neural networks and physics, and how the number of possible problems that we care about in physics is an infinitesimal fraction of all possible problems that can be posed.