Skip to content

Human Compatible chapters

About this audiobook · Recording details

Recording raphael-corkhill-2019 · Narrated by Raphael Corkhill

63 chapters

Chapter titles and times
ChapterTitleStartDuration
1Opening Credits0:00:000:00:26.075
2Preface0:00:26.0750:00:02.995
3Why this Book? Why Now?0:00:29.0700:01:09.606
4Overview of the Book0:01:38.6760:01:06.626
51. If We Succeed0:02:45.3020:07:25.651
6How Did We Get Here?0:10:10.9530:05:35.169
7What Happens Next?0:15:46.1220:04:54.350
8What Went Wrong?0:20:40.4720:04:42.700
9Can We Fix It?0:25:23.1720:02:19.607
102. Intelligence in Humans and Machines0:27:42.7790:00:54.216
11Intelligence0:28:36.9950:46:36.795
12Computers1:15:13.7900:21:13.109
13Intelligent Computers1:36:26.8990:56:07.868
143. How Might AI Progress in the Future?2:32:34.7670:00:05.927
15The Near Future2:32:40.6940:33:43.243
16When Will Superintelligent AI Arrive?3:06:23.9370:04:37.523
17Conceptual Breakthroughs to Come3:11:01.4600:35:59.983
18Imagining a Superintelligent Machine3:47:01.4430:08:24.660
19The Limits of Superintelligence3:55:26.1030:05:07.780
20How Will AI Benefit Humans?4:00:33.8830:10:32.195
214. Misuses of AI4:11:06.0780:00:35.201
22Surveillance, Persuasion, and Control4:11:41.2790:17:35.233
23Lethal Autonomous Weapons4:29:16.5120:07:46.770
24Eliminating Work as We Know It4:37:03.2820:25:00.332
25Usurping Other Human Roles5:02:03.6140:16:25.894
265. Overly Intelligent AI5:18:29.5080:00:06.078
27The Gorilla Problem5:18:35.5860:10:43.517
28The King Midas Problem5:29:19.1030:10:26.301
29Fear and Greed: Instrumental Goals5:39:45.4040:03:55.299
30Intelligence Explosions5:43:40.7030:06:38.042
316. The Not-So-Great AI Debate5:50:18.7450:02:42.999
32Denial5:53:01.7440:19:42.594
33Deflection6:12:44.3380:11:25.201
34Tribalism6:24:09.5390:03:44.491
35Can’t We Just...6:27:54.0300:21:27.289
36The Debate, Restarted6:49:21.3190:02:40.451
377. AI: A Different Approach6:52:01.7700:03:35.928
38Principles for Beneficial Machines6:55:37.6980:16:43.314
39Reasons for Optimism7:12:21.0120:06:00.869
40Reasons for Caution7:18:21.8810:04:31.518
418. Provably Beneficial AI7:22:53.3990:01:26.795
42Mathematical Guarantees7:24:20.1940:13:47.648
43Learning Preferences from Behavior7:38:07.8420:06:56.332
44Assistance Games7:45:04.1740:24:24.760
45Requests and Instructions8:09:28.9340:05:41.088
46Wireheading8:15:10.0220:07:59.340
47Recursive Self-Improvement8:23:09.3620:05:30.872
489. Complications: Us8:28:40.2340:01:26.817
49Different Humans8:30:07.0510:03:41.177
50Many Humans8:33:48.2280:33:52.763
51Nice, Nasty, and Envious Humans9:07:40.9910:11:57.455
52Stupid, Emotional Humans9:19:38.4460:09:06.740
53Do Humans Really Have Preferences?9:28:45.1860:25:36.457
5410. Problem Solved?9:54:21.6430:01:25.644
55Beneficial Machines9:55:47.2870:05:48.149
56Governance of AI10:01:35.4360:09:37.141
57Misuse10:11:12.5770:02:47.468
58Enfeeblement and Human Autonomy10:14:00.0450:06:10.043
59Appendix A: Searching for Solutions10:20:10.0880:18:12.243
60Appendix B: Knowledge and Logic10:38:22.3310:13:32.976
61Appendix C: Uncertainty and Probability10:51:55.3070:23:54.204
62Appendix D: Learning from Experience11:15:49.5110:21:42.718
63End Credits11:37:32.2290:00:38.557