Robert Miles AI Safety

@UCLB7AzTwc6VFZrBsO2ucBMg - 169K subscribers

Videos about Artificial Intelligence Safety Research, for everyone. AI is leaping forward right now, it's only a matter of time before we develop true Artificial General Intelligence, and there are a lot of different ways that this could go badly wrong for us. Putting aside the science fiction, this channel is about AI Safety research - humanity's best attempt to foresee the problems AI might pose and work out ways to ensure that our AI developments are safe and beneficial.

Home Videos Live Playlists

Tech is Good, AI Will Be Different

Tech is Good, AI Will Be Different Robert Miles AI Safety

65K views - 6 months ago

AI Safety Career Advice! (And So Can You!)

AI Safety Career Advice! (And So Can You!) Robert Miles AI Safety

72.1K views - 9 months ago

Using Dangerous AI, But Safely?

Using Dangerous AI, But Safely? Robert Miles AI Safety

146.7K views - 1 year ago

AI Ruined My Year

AI Ruined My Year Robert Miles AI Safety

267.6K views - 1 year ago

Why Does AI Lie, and What Can We Do About It?

Why Does AI Lie, and What Can We Do About It? Robert Miles AI Safety

277.2K views - 3 years ago

We Were Right! Real Inner Misalignment

We Were Right! Real Inner Misalignment Robert Miles AI Safety

265.1K views - 4 years ago

Intro to AI Safety, Remastered

Intro to AI Safety, Remastered Robert Miles AI Safety

191.3K views - 4 years ago

Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think...

Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... Robert Miles AI Safety

90.9K views - 4 years ago

The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment

The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment Robert Miles AI Safety

262.3K views - 5 years ago

Quantilizers: AI That Doesn't Try Too Hard

Quantilizers: AI That Doesn't Try Too Hard Robert Miles AI Safety

88.9K views - 5 years ago

Sharing the Benefits of AI: The Windfall Clause

Sharing the Benefits of AI: The Windfall Clause Robert Miles AI Safety

81.8K views - 5 years ago

10 Reasons to Ignore AI Safety

10 Reasons to Ignore AI Safety Robert Miles AI Safety

358.8K views - 5 years ago

9 Examples of Specification Gaming

9 Examples of Specification Gaming Robert Miles AI Safety

322K views - 5 years ago

Training AI Without Writing A Reward Function, with Reward Modelling

Training AI Without Writing A Reward Function, with Reward Modelling Robert Miles AI Safety

253.6K views - 6 years ago

AI That Doesn't Try Too Hard - Maximizers and Satisficers

AI That Doesn't Try Too Hard - Maximizers and Satisficers Robert Miles AI Safety

211.4K views - 6 years ago

Is AI Safety a Pascal's Mugging?

Is AI Safety a Pascal's Mugging? Robert Miles AI Safety

384.5K views - 6 years ago

A Response to Steven Pinker on AI

A Response to Steven Pinker on AI Robert Miles AI Safety

213.6K views - 6 years ago

How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification

How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification Robert Miles AI Safety

178.8K views - 6 years ago

Why Not Just: Think of AGI Like a Corporation?

Why Not Just: Think of AGI Like a Corporation? Robert Miles AI Safety

161.7K views - 7 years ago

Safe Exploration: Concrete Problems in AI Safety Part 6

Safe Exploration: Concrete Problems in AI Safety Part 6 Robert Miles AI Safety

100K views - 7 years ago

Friend or Foe? AI Safety Gridworlds extra bit

Friend or Foe? AI Safety Gridworlds extra bit Robert Miles AI Safety

44.1K views - 7 years ago

AI Safety Gridworlds

AI Safety Gridworlds Robert Miles AI Safety

94.7K views - 7 years ago

Experts' Predictions about the Future of AI

Experts' Predictions about the Future of AI Robert Miles AI Safety

81.2K views - 7 years ago

Why Would AI Want to do Bad Things? Instrumental Convergence

Why Would AI Want to do Bad Things? Instrumental Convergence Robert Miles AI Safety

264.5K views - 7 years ago

Superintelligence Mod for Civilization V

Superintelligence Mod for Civilization V Robert Miles AI Safety

70.9K views - 8 years ago

Intelligence and Stupidity: The Orthogonality Thesis

Intelligence and Stupidity: The Orthogonality Thesis Robert Miles AI Safety

697.5K views - 8 years ago

Scalable Supervision: Concrete Problems in AI Safety Part 5

Scalable Supervision: Concrete Problems in AI Safety Part 5 Robert Miles AI Safety

54.2K views - 8 years ago

AI Safety at EAGlobal2017 Conference

AI Safety at EAGlobal2017 Conference Robert Miles AI Safety

19.5K views - 8 years ago

AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes #1

AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes #1 Robert Miles AI Safety

48.9K views - 8 years ago

What can AGI do? I/O and Speed

What can AGI do? I/O and Speed Robert Miles AI Safety

123K views - 8 years ago

What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4

What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4 Robert Miles AI Safety

117.1K views - 8 years ago

Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5

Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5 Robert Miles AI Safety

94.6K views - 8 years ago

The other "Killer Robot Arms Race" Elon Musk should worry about

The other "Killer Robot Arms Race" Elon Musk should worry about Robert Miles AI Safety

100.8K views - 8 years ago

Reward Hacking: Concrete Problems in AI Safety Part 3

Reward Hacking: Concrete Problems in AI Safety Part 3 Robert Miles AI Safety

107.7K views - 8 years ago

Why Not Just: Raise AI Like Kids?

Why Not Just: Raise AI Like Kids? Robert Miles AI Safety

173K views - 8 years ago

Empowerment: Concrete Problems in AI Safety part 2

Empowerment: Concrete Problems in AI Safety part 2 Robert Miles AI Safety

69K views - 8 years ago

Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5

Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5 Robert Miles AI Safety

55.1K views - 8 years ago

Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1

Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1 Robert Miles AI Safety

158.4K views - 8 years ago

Are AI Risks like Nuclear Risks?

Are AI Risks like Nuclear Risks? Robert Miles AI Safety

99.8K views - 8 years ago

Respectability Robert Miles AI Safety

80K views - 8 years ago

Predicting AI: RIP Prof. Hubert Dreyfus

Predicting AI: RIP Prof. Hubert Dreyfus Robert Miles AI Safety

62.9K views - 8 years ago

What's the Use of Utility Functions?

What's the Use of Utility Functions? Robert Miles AI Safety

67.8K views - 8 years ago

Where do we go now?

Where do we go now? Robert Miles AI Safety

72.6K views - 8 years ago

Status Report Robert Miles AI Safety

18.2K views - 8 years ago

Channel Introduction

Channel Introduction Robert Miles AI Safety

54.1K views - 9 years ago