2023-04-28 | Apply to Study AI Safety Now! #shorts | 1:00 | 42,816 | |
|
2023-02-21 | My 3-Month fellowship to write about AI Safety! #shorts | 1:00 | 3,530 | |
|
2022-12-09 | Why Does AI Lie, and What Can We Do About It? | 9:24 | 246,832 | |
|
2022-11-11 | Apply Now for a Paid Residency on Interpretability #short | 0:45 | 16,484 | |
|
2022-10-14 | $100,000 for Tasks Where Bigger AIs Do Worse Than Smaller Ones #short | 1:00 | 29,261 | |
|
2022-05-24 | Free ML Bootcamp for Alignment #shorts | 0:52 | 19,005 | |
|
2022-02-08 | Win $50k for Solving a Single AI Problem? #Shorts | 1:00 | 485,088 | |
|
2021-11-19 | Apply to AI Safety Camp! #shorts | 1:00 | 25,893 | |
|
2021-10-10 | We Were Right! Real Inner Misalignment | 11:47 | 241,694 | |
|
2021-06-24 | Intro to AI Safety, Remastered | 18:05 | 146,843 | |
|
2021-05-23 | Deceptive Misaligned Mesa-Optimisers? It's More Likely Than You Think... | 10:20 | 81,874 | |
|
2021-02-16 | The OTHER AI Alignment Problem: Mesa-Optimizers and Inner Alignment | 23:24 | 219,015 | |
|
2020-12-13 | Quantilizers: AI That Doesn't Try Too Hard | 9:54 | 83,001 | |
|
2020-07-06 | Sharing the Benefits of AI: The Windfall Clause | 11:44 | 78,057 | |
|
2020-06-04 | 10 Reasons to Ignore AI Safety | 16:29 | 334,821 | |
|
2020-04-29 | 9 Examples of Specification Gaming | 9:40 | 302,986 | |
|
2019-12-13 | Training AI Without Writing A Reward Function, with Reward Modelling | 17:52 | 227,750 | |
|
2019-08-23 | AI That Doesn't Try Too Hard - Maximizers and Satisficers | 10:22 | 198,262 | |
|
2019-05-16 | Is AI Safety a Pascal's Mugging? | 13:41 | 363,001 | |
|
2019-03-31 | A Response to Steven Pinker on AI | 15:38 | 200,722 | |
|
2019-03-11 | How to Keep Improving When You're Better Than Any Teacher - Iterated Distillation and Amplification | 11:32 | 163,019 | |
|
2018-12-23 | Why Not Just: Think of AGI Like a Corporation? | 15:27 | 151,099 | |
|
2018-09-21 | Safe Exploration: Concrete Problems in AI Safety Part 6 | 13:46 | 92,976 | |
|
2018-06-24 | Friend or Foe? AI Safety Gridworlds extra bit | 3:47 | 40,234 | |
|
2018-05-25 | AI Safety Gridworlds | 7:23 | 89,218 | |
|
2018-03-31 | Experts' Predictions about the Future of AI | 6:47 | 78,581 | |
|
2018-03-24 | Why Would AI Want to do Bad Things? Instrumental Convergence | 10:36 | 236,594 | |
|
2018-02-13 | Superintelligence Mod for Civilization V | 1:04:40 | 68,677 | | Civilization V
|
2018-01-11 | Intelligence and Stupidity: The Orthogonality Thesis | 13:03 | 647,198 | |
|
2017-11-29 | Scalable Supervision: Concrete Problems in AI Safety Part 5 | 5:03 | 49,415 | |
|
2017-11-16 | AI Safety at EAGlobal2017 Conference | 5:30 | 18,756 | |
|
2017-10-29 | AI learns to Create ̵K̵Z̵F̵ ̵V̵i̵d̵e̵o̵s̵ Cat Pictures: Papers in Two Minutes #1 | 5:20 | 47,392 | |
|
2017-10-17 | What can AGI do? I/O and Speed | 10:41 | 115,086 | |
|
2017-09-24 | What Can We Do About Reward Hacking?: Concrete Problems in AI Safety Part 4 | 9:38 | 109,736 | |
|
2017-08-29 | Reward Hacking Reloaded: Concrete Problems in AI Safety Part 3.5 | 7:32 | 88,235 | |
|
2017-08-22 | The other "Killer Robot Arms Race" Elon Musk should worry about | 5:51 | 98,147 | |
|
2017-08-12 | Reward Hacking: Concrete Problems in AI Safety Part 3 | 6:56 | 98,639 | |
|
2017-07-22 | Why Not Just: Raise AI Like Kids? | 5:51 | 166,522 | |
|
2017-07-09 | Empowerment: Concrete Problems in AI Safety part 2 | 6:33 | 65,473 | |
|
2017-06-25 | Avoiding Positive Side Effects: Concrete Problems in AI Safety part 1.5 | 3:23 | 50,724 | |
|
2017-06-18 | Avoiding Negative Side Effects: Concrete Problems in AI Safety part 1 | 9:33 | 150,511 | |
|
2017-06-17 | Robert Miles Live Stream | 0:00 | 0 | |
|
2017-06-10 | Are AI Risks like Nuclear Risks? | 10:13 | 95,434 | |
|
2017-05-27 | Respectability | 5:04 | 76,724 | |
|
2017-05-18 | Predicting AI: RIP Prof. Hubert Dreyfus | 8:17 | 59,957 | |
|
2017-04-27 | What's the Use of Utility Functions? | 7:04 | 63,796 | |
|
2017-03-31 | Where do we go now? | 7:45 | 70,431 | |
|
2017-03-18 | Status Report | 1:26 | 17,325 | |
|
2017-02-28 | Channel Introduction | 1:05 | 52,330 | |
|