robert mueller
No strong matches for “robert mueller”. Here are the closest videos.
9:33Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1
161K views • 9 years ago
Robert Miles AI Safety
Robert Miles introduces the first of several videos on the paper 'Concrete Problems in AI Safety', focusing on how AI systems can cause accidental negative side effects. It explains the problem in accessible terms.
10:36Why Would AI Want to do Bad Things? Instrumental Convergence
274K views • 8 years ago
Robert Miles AI Safety
Robert Miles explains instrumental convergence: why an AGI with almost any goal would tend to pursue sub-goals like self-preservation and resource acquisition. It builds on Omohundro's basic AI drives and his orthogonality thesis video.
13:03Intelligence and Stupidity: The Orthogonality Thesis
710K views • 8 years ago
Robert Miles AI Safety
Robert Miles explains the orthogonality thesis: how an agent can be highly intelligent while pursuing goals that seem stupid or alien to humans. He separates intelligence from goals and touches on the stamp-collector example.
15:27Why Not Just: Think of AGI Like a Corporation?
163K views • 7 years ago
Robert Miles AI Safety
Robert Miles asks whether corporations can be thought of as artificial general superintelligences and how far the analogy holds. He argues the differences, such as being limited by employees' capabilities, matter for AI safety.
13:44Is AI Safety a Pascal's Mugging?
388K views • 7 years ago
Robert Miles AI Safety
Robert Miles examines whether the case for AI safety is a Pascal's mugging, a tiny probability of an enormous payoff. He argues it is not, because AI risk does not depend on vanishingly small probabilities.
16:2910 Reasons to Ignore AI Safety
363K views • 6 years ago
Robert Miles AI Safety
Robert Miles goes through ten common reasons people give for dismissing AI safety, adapted from Stuart Russell's list, and answers each one. It is aimed at skeptics and newcomers.
17:52Training AI Without Writing A Reward Function, with Reward Modelling
259K views • 6 years ago
Robert Miles AI Safety
Robert Miles explains reward modelling, in which an AI learns what humans want from their preference comparisons instead of a hand-written reward function. He walks through the 2017 paper on deep reinforcement learning from human preferences.
11:47We Were Right! Real Inner Misalignment
271K views • 5 years ago
Robert Miles AI Safety
Robert Miles covers a paper where researchers ran real versions of his earlier mesa-optimizer thought experiments. They show inner misalignment, where an AI learns the wrong goal in training and misbehaves when deployed.
9:09England: South Sea Bubble - The Sharp Mind of John Blunt - Extra History - Part 1
3.5M views • 11 years ago
Extra History
The first part of Extra History's animated miniseries on the South Sea Bubble. It explains how England's government debt led Robert Harley to turn to financier John Blunt, whose schemes began inflating artificial demand for shares.
13:13The Nuclear Salt Water Rocket - Possibly the Craziest Rocket Engine Ever Imagined.
970K views • 5 years ago
Scott Manley
Scott Manley explains the nuclear salt water rocket, Robert Zubrin's concept of a rocket fueled by a rapid nuclear reaction in uranium salt dissolved in water. He covers its extraordinary performance and the dangers of managing it.