| Video name | Likes | Views | Published |
|---|
| "Don't Fear The Terminator" - Yann LeCun on Facebook | 28 | 133 | 14 October 2019 17:27:16 |
| 10 Reasons to Ignore AI Safety | 10,230 | 147,009 | 4 June 2020 15:28:37 |
| 9 Examples of Specification Gaming | 16,848 | 209,406 | 29 April 2020 16:41:20 |
| A Response to Steven Pinker on AI | 8,731 | 146,354 | 31 March 2019 13:39:12 |
| AI Safety Gridworlds | 3,085 | 67,344 | 25 May 2018 16:20:46 |
| AI Safety at EAGlobal2017 Conference | 1,090 | 15,703 | 16 November 2017 19:21:00 |
| AI That Doesn't Try Too Hard - Maximizers and Satisficers | 8,090 | 145,589 | 23 August 2019 15:05:26 |
| AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes | 2,799 | 43,191 | 29 October 2017 11:49:20 |
| Are AI Risks like Nuclear Risks? | 3,370 | 65,671 | 10 June 2017 15:22:46 |
| Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1 | 4,252 | 129,016 | 18 June 2017 11:02:16 |
| Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5 | 2,172 | 39,765 | 25 June 2017 09:29:27 |
| Channel Introduction | 1,311 | 47,243 | 28 February 2017 20:14:23 |
| Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... | 3,949 | 31,924 | 23 May 2021 20:15:57 |
| Empowerment: Concrete Problems in AI Safety part 2 | 2,692 | 52,820 | 9 July 2017 09:24:11 |
| Experts' Predictions about the Future of AI | 3,391 | 63,797 | 31 March 2018 12:12:37 |
| Friend or Foe? AI Safety Gridworlds extra bit | 1,641 | 29,363 | 24 June 2018 23:31:07 |
| How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification | 7,373 | 115,472 | 11 March 2019 12:14:21 |
| Intelligence and Stupidity: The Orthogonality Thesis | 18,642 | 269,272 | 11 January 2018 19:53:43 |
| Intro to AI Safety, Remastered | 2,522 | 18,214 | 24 June 2021 15:25:40 |
| Is AI Safety a Pascal's Mugging? | 13,956 | 223,270 | 16 May 2019 14:11:07 |
| MAXIMUM OVERGEORGIA | 598 | 8,158 | 4 June 2016 00:04:12 |
| Much Better Stampy Test Video | 0 | 70 | 15 March 2021 20:25:14 |
| PC Build Video! | 84 | 724 | 28 April 2017 13:56:19 |
| Predicting AI: RIP Prof. Hubert Dreyfus | 2,987 | 47,212 | 18 May 2017 12:25:34 |
| Quantilizers: AI That Doesn't Try Too Hard | 4,440 | 44,016 | 13 December 2020 20:46:21 |
| Reading and Commenting On Pinker's Article | 22 | 180 | 28 March 2019 18:10:03 |
| Respectability | 3,121 | 51,938 | 27 May 2017 14:06:29 |
| Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5 | 3,352 | 68,080 | 29 August 2017 10:08:41 |
| Reward Hacking: Concrete Problems in AI Safety Part 3 | 3,642 | 76,080 | 12 August 2017 19:24:08 |
| Safe Exploration: Concrete Problems in AI Safety Part 6 | 3,312 | 65,707 | 21 September 2018 11:20:53 |
| Scalable Supervision: Concrete Problems in AI Safety Part 5 | 1,996 | 37,378 | 29 November 2017 21:47:29 |
| Sharing the Benefits of AI: The Windfall Clause | 5,929 | 59,466 | 6 July 2020 16:53:53 |
| Status Report | 1,001 | 15,053 | 18 March 2017 11:40:43 |
| Superintelligence Mod for Civilization V | 1,595 | 57,488 | 13 February 2018 17:17:58 |
| The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment | 7,689 | 73,088 | 16 February 2021 18:37:00 |
| The other "Killer Robot Arms Race" Elon Musk should worry about | 4,708 | 78,965 | 22 August 2017 11:19:33 |
| Training AI Without Writing A Reward Function, with Reward Modelling | 10,953 | 154,430 | 13 December 2019 16:39:11 |
| Untitled2 | 158 | 5,976 | 27 August 2017 22:12:27 |
| We Were Right! Real Inner Misalignment | 5,400 | 42,844 | 10 October 2021 |
| What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4 | 3,771 | 82,269 | 24 September 2017 12:09:54 |
| What can AGI do? I/O and Speed | 4,735 | 82,772 | 17 October 2017 10:20:35 |
| What's the Use of Utility Functions? | 2,908 | 50,424 | 27 April 2017 19:35:30 |
| Where do we go now? | 2,697 | 62,011 | 31 March 2017 20:16:27 |
| Why Not Just: Raise AI Like Kids? | 8,100 | 134,353 | 22 July 2017 13:58:34 |
| Why Not Just: Think of AGI Like a Corporation? | 6,462 | 113,207 | 23 December 2018 20:01:39 |
| Why Would AI Want to do Bad Things? Instrumental Convergence | 9,590 | 157,051 | 24 March 2018 19:51:39 |
