Pages with the most revisions

Showing below up to 100 results in range #21 to #120.

View (previous 100 | next 100) (20 | 50 | 100 | 250 | 500)

21. My understanding of how IDA works‏‎ (23 revisions)
22. Medium that reveals flaws‏‎ (22 revisions)
23. There is room for something like RAISE‏‎ (21 revisions)
24. The Hour I First Believed‏‎ (21 revisions)
25. Soft-hard takeoff‏‎ (21 revisions)
26. Comparison of AI takeoff scenarios‏‎ (21 revisions)
27. AlphaGo‏‎ (20 revisions)
28. Credit card research 2021‏‎ (20 revisions)
29. List of success criteria for HRAD work‏‎ (20 revisions)
30. Explorable explanation‏‎ (19 revisions)
31. SuperMemo shortcuts‏‎ (19 revisions)
32. Analyzing disagreements‏‎ (18 revisions)
33. My current thoughts on the technical AI safety pipeline (outside academia)‏‎ (18 revisions)
34. Spaced proof review is not about memorizing proofs‏‎ (18 revisions)
35. Convergent evolution of values‏‎ (18 revisions)
36. Human safety problem‏‎ (17 revisions)
37. Lumpiness‏‎ (17 revisions)
38. List of teams at OpenAI‏‎ (17 revisions)
39. Spaced proof review routine‏‎ (17 revisions)
40. Improvement curve for good people‏‎ (16 revisions)
41. Spoiler test of depth‏‎ (16 revisions)
42. Asymmetric institution‏‎ (16 revisions)
43. MIRI vs Paul research agenda hypotheses‏‎ (15 revisions)
44. Main Page‏‎ (14 revisions)
45. Interaction reversal between knowledge-to-be-memorized and ideas-to-be-developed‏‎ (14 revisions)
46. Duolingo‏‎ (13 revisions)
47. Hardware argument for AI timelines‏‎ (13 revisions)
48. Anki deck philosophy‏‎ (13 revisions)
49. Jelly no Puzzle‏‎ (12 revisions)
50. Duolingo for math‏‎ (12 revisions)
51. Science argument‏‎ (11 revisions)
52. Goalpost for usefulness of HRAD work‏‎ (11 revisions)
53. Incremental reading in Anki‏‎ (11 revisions)
54. Narrow vs broad cognitive augmentation‏‎ (11 revisions)
55. List of reasons something isn't popular or successful‏‎ (10 revisions)
56. 3Blue1Brown‏‎ (10 revisions)
57. Add all permutations of a card to prevent pattern-matching‏‎ (10 revisions)
58. AI safety field consensus‏‎ (10 revisions)
59. Finiteness assumption in explorable media‏‎ (10 revisions)
60. Spaced repetition is not about memorization‏‎ (10 revisions)
61. Emotional difficulties of spaced repetition‏‎ (10 revisions)
62. List of terms used to describe the intelligence of an agent‏‎ (10 revisions)
63. Probability and statistics as fields with an exploratory medium‏‎ (10 revisions)
64. Deck options for proof cards‏‎ (10 revisions)
65. Why ain'tcha better at math‏‎ (10 revisions)
66. Tips for reviving a spaced repetition practice‏‎ (10 revisions)
67. Desiderata for dissolving the question‏‎ (10 revisions)
68. Narrow window argument against continuous takeoff‏‎ (9 revisions)
69. Ongoing friendship and collaboration is important‏‎ (9 revisions)
70. Reverse side card for everything‏‎ (9 revisions)
71. Progress in self-improvement‏‎ (9 revisions)
72. Popularity symbiosis‏‎ (9 revisions)
73. Braid for math‏‎ (9 revisions)
74. Spaced writing inbox‏‎ (9 revisions)
75. Spaced repetition allows graceful deprecation of experiments‏‎ (9 revisions)
76. Expert response heuristic for prompt writing‏‎ (9 revisions)
77. Switching costs of various kinds of software‏‎ (9 revisions)
78. The Precipice notes‏‎ (8 revisions)
79. Evolution‏‎ (8 revisions)
80. Can spaced repetition interfere with internal sense of relevance?‏‎ (8 revisions)
81. Choosing problems for spaced proof review‏‎ (8 revisions)
82. List of timelines for futuristic technologies‏‎ (8 revisions)
83. Coherence and goal-directed agency discussion‏‎ (8 revisions)
84. Tinkering in math requires loading the situation into working memory‏‎ (8 revisions)
85. Competence gap‏‎ (8 revisions)
86. Linked list proof card‏‎ (8 revisions)
87. Deck options for small cards‏‎ (8 revisions)
88. Unbounded working memory assumption in explanations‏‎ (8 revisions)
89. Christiano's operationalization of slow takeoff‏‎ (8 revisions)
90. Nobody understands what makes people snap into AI safety‏‎ (8 revisions)
91. Online question-answering services are unreliable‏‎ (8 revisions)
92. Optimal unlocking mechanism for booster cards is unclear‏‎ (8 revisions)
93. Hyperbolic growth‏‎ (8 revisions)
94. Self-graded prompts made for others must provide guidance for grading‏‎ (8 revisions)
95. Simple core of consequentialist reasoning‏‎ (8 revisions)
96. Booster card‏‎ (7 revisions)
97. Spaced repetition experiments take months to complete‏‎ (7 revisions - redirect page)
98. Pivotal act‏‎ (7 revisions)
99. Importance of knowing about AI takeoff‏‎ (7 revisions)
100. Cognitive biases that are opposites of each other‏‎ (7 revisions)
101. List of people who have thought a lot about spaced repetition‏‎ (7 revisions)
102. Agent foundations‏‎ (7 revisions)
103. The Secret of Psalm 46 outline‏‎ (7 revisions)
104. AI safety lacks a space to ask stupid or ballsy questions‏‎ (7 revisions)
105. The Secret of Psalm 46‏‎ (7 revisions)
106. Different senses of claims about AGI‏‎ (7 revisions)
107. AI safety is harder than most things‏‎ (7 revisions)
108. List of breakthroughs plausibly needed for AGI‏‎ (7 revisions)
109. Is AI safety no longer a scenius?‏‎ (7 revisions)
110. Emotional difficulties of AI safety research‏‎ (7 revisions)
111. Creative forgetting‏‎ (7 revisions)
112. Spaced inbox ideas‏‎ (7 revisions)
113. Snoozing epicycle‏‎ (7 revisions)
114. Instruction manuals vs giving the answers‏‎ (6 revisions)
115. Iterated amplification‏‎ (6 revisions)
116. Spaced repetition‏‎ (6 revisions)
117. Sudden emergence‏‎ (6 revisions)
118. Unintended consequences of AI safety advocacy argument against AI safety‏‎ (6 revisions)
119. Mass shift to technical AI safety research is suspicious‏‎ (6 revisions)
120. The Witness‏‎ (6 revisions)

View (previous 100 | next 100) (20 | 50 | 100 | 250 | 500)