User contributions
(newest | oldest) View (newer 50 | older 50) (20 | 50 | 100 | 250 | 500)
- 02:11, 20 April 2020 (diff | hist) . . (+407) . . N Finiteness assumption in explorable media (Created page with "Explorable and interactive media seem to bake in an assumption of finiteness, which makes it challenging to interact with the infinite and arbitrary objects that appear in mat...")
- 22:20, 16 April 2020 (diff | hist) . . (+1,306) . . N AI will solve everything argument against AI safety (Created page with "My understanding of this argument is that if we get AGI, that will solve all of our other problems. So we should try to get there as fast as possible, without worrying about A...")
- 07:44, 16 April 2020 (diff | hist) . . (+1,547) . . N Personhood API vs therapy axis of interpersonal interactions (Created page with "Building off of: * https://meltingasphalt.com/personhood-a-game-for-two-or-more-players/ * https://www.greaterwrong.com/posts/uxYemA2ttzjs8z8Eb/drive-by-low-effort-criticism/...")
- 02:24, 16 April 2020 (diff | hist) . . (+722) . . N Selection effect for successful formalizations (Created page with "It's possible to point to some successful formalizations of things, like formalizing math, or formalizing computation. But there is a selection effect here because we are...")
- 03:01, 15 April 2020 (diff | hist) . . (+698) . . N The Precipice notes (Created page with "* "If we are the only moral agents that will ever arise in our universe—the only beings capable of making choices on the grounds of what is right and wrong—then responsibi...")
- 07:46, 8 April 2020 (diff | hist) . . (+674) . . N Tao Analysis I exercise count (Created page with "chapters 1-11: <pre>>>> (0 + 0) + (0 + 6 + 5) + (11 + 3 + 8 + 11 + 13 + 10) + (8 + 6 + 5 + 3) + (1 + 2 + 5 + 8 + 5 + 3) + (10 + 2 + 4 + 10 + 3 + 5 + 1) + (5 + 6 + 3 + 1 + 3)...")
- 07:03, 8 April 2020 (diff | hist) . . (+1,660) . . N Website to aggregate solutions to textbook exercises (Created page with "Why isn't there a website that pays users to submit solutions to textbook exercises, and then charges people to read those answers? it seems like many students are already do...")
- 06:17, 5 April 2020 (diff | hist) . . (+53) . . N Kasparov window (Created page with "https://www.google.com/search?q=%22kasparov+window%22")
- 23:01, 31 March 2020 (diff | hist) . . (+323) . . N Statistical analysis of expert timelines argument for AI timelines (Created page with "This is a kind of higher-order/meta-level argument that simply performs a statistical analysis of experts' AI timelines to come up with some overall estimate of AI timelines....")
- 22:58, 31 March 2020 (diff | hist) . . (+323) . . N Category:AI timelines arguments (Created page with "An AI timelines argument gives a self-contained account of when humans are expected to create an AGI. In other words, the pages in this category do not simply give evi...")
- 22:52, 31 March 2020 (diff | hist) . . (+527) . . N Laplace's rule of succession argument for AI timelines (Created page with "The '''Laplace's rule of succession argument for AI timelines''' uses Laplace's rule of succession to estimate when humans will create AGI. Th...")
- 09:10, 31 March 2020 (diff | hist) . . (+1,706) . . N Probability and statistics as fields with an exploratory medium (Created page with "Something I've noticed about probability and statistics is that when I'm working on something (most recently, I was thinking about [https://stacky.net/wiki/index.php?title=Aga...")
- 04:36, 28 March 2020 (diff | hist) . . (+611) . . N List of men by number of sons, daughters, and wives (Created page with "List of men along with their number of sons, daughters, and wives. {| class="sortable wikitable" ! Name !! Sons !! Daughters !! Children (sons + daughters) !! Wives !! Source...")
- 05:19, 26 March 2020 (diff | hist) . . (+342) . . N List of experiments with Anki (Created page with "On this page, I want to keep a list of experiments that I have tried or am currently trying with Anki. These experiments aren't formal (I don't do any rigorous data collection...")
- 08:55, 19 March 2020 (diff | hist) . . (+848) . . N Popularity symbiosis (Created page with "one of the things i've noticed is that i find people by looking for discussions of more famous people. e.g. i might find some random person's blog by searching for keith frank...")
- 08:50, 19 March 2020 (diff | hist) . . (+4,864) . . N Interacting with copies of myself (Created page with "(this is really crazy; don't read this) how should i interact with other copies of myself? sometimes there are people who think so similarly to you, who are value-aligned, et...")
- 08:18, 19 March 2020 (diff | hist) . . (+1,196) . . N Convergent evolution of values (Created page with "multiplicative process => log-resource utility function i think there can be lots of similar, robust phenomena like this, for evolved organisms. so in terms of six plausible...")
- 23:46, 15 March 2020 (diff | hist) . . (+152) . . N The Hour I First Believed (Created page with "'''"The Hour I First Believed"''' is a blog post by Scott Alexander about acausal trade and a big picture of what will happen in the multiverse.")
- 04:12, 15 March 2020 (diff | hist) . . (+18) . . N Test (Created page with "test <comments />")
- 01:25, 10 March 2020 (diff | hist) . . (+726) . . N AI prepping (Created page with ""As to the final step, I’m not claiming that AI is an extinction risk. I think that it’s not clear that even an AI that went badly wrong would want to kill everyone. I thi...")
- 00:46, 10 March 2020 (diff | hist) . . (+1,055) . . N Late singularity (Created page with "here "late singularity" means something like "the singularity happens 200+ years from now, rather than like 20 years or 100 years". are late singularities actually better? if...")
- 21:09, 8 March 2020 (diff | hist) . . (+294) . . N UDASSA (Created page with "'''UDASSA''' (sometimes also written '''UD+ASSA''' to make the two components clear) is a theory of anthropics. ==Etymology== The name "UDASSA" comes from "universal distrib...")
- 08:16, 8 March 2020 (diff | hist) . . (+94) . . N List of big discussions in AI alignment (Created page with "* Coherence and goal-directed agency discussion * Realism about rationality discussion")
- 22:52, 7 March 2020 (diff | hist) . . (+791) . . N Selection effect for who builds AGI (Created page with ""But also, what I’m more worried about is that the arguments will always be a bit uncertain, and that they will be the kind of arguments that maybe should push a rational pe...")
- 07:42, 5 March 2020 (diff | hist) . . (+187) . . N MIRI vs Paul research agenda hypotheses (Created page with "from "The concern" in https://agentfoundations.org/item?id=1220 key hopes listed in https://www.greaterwrong.com/posts/HCv2uwgDGf5dyX5y6/preface-to-the-sequence-on-iterated-a...")
- 22:35, 1 March 2020 (diff | hist) . . (+3,114) . . N Comparison of terms related to agency (Created page with "{| class="wikitable" ! Term !! Opposite |- | Agent || |- | Optimizer, optimization process || |- | consequentialist || |- | expected utility maximizer || |- | goal-directed, g...")
- 04:33, 27 February 2020 (diff | hist) . . (+73) . . N Terms used to describe intelligence of agents (Issa moved page Terms used to describe intelligence of agents to List of terms used to describe the intelligence of an agent) (current) (Tag: New redirect)
- 04:31, 27 February 2020 (diff | hist) . . (+421) . . N List of terms used to describe the intelligence of an agent (Created page with "Eliezer has lots of terms to describe how intelligent/powerful/whatever an agent is. * Relevant * Pivotal (is this only for actions, or also for agents, as in "agent who...")
- 03:30, 27 February 2020 (diff | hist) . . (+529) . . N Coherence and goal-directed agency discussion (Created page with "https://www.greaterwrong.com/posts/vphFJzK3mWA4PJKAg/coherent-behaviour-in-the-real-world-is-an-incoherent#comment-F2YB5aJgDdK9ZGspw https://www.greaterwrong.com/posts/NxF5G6...")
- 04:33, 26 February 2020 (diff | hist) . . (+381) . . N Simple core (Created page with "'''Simple core''' is a term that has been used to describe various things in AI safety. * Simple core to corrigibility<ref>https://ai-alignment.com/corrigibility-3039e668...")
- 23:27, 25 February 2020 (diff | hist) . . (+359) . . N Agent foundations (Created page with "==Terminology== There are many different terms used to describe MIRI's research, and it's a little unclear how careful people are when using these terms. * agent foundations...")
- 07:42, 25 February 2020 (diff | hist) . . (+34) . . N Uncertain Future (Redirected page to The Uncertain Future) (current) (Tag: New redirect)
- 03:54, 25 February 2020 (diff | hist) . . (+27) . . N Wei Dai (Created page with "aka distributor of weipills")
- 03:31, 25 February 2020 (diff | hist) . . (+362) . . N AI safety field consensus (Created page with "People in AI safety tend to disagree about many things. However, there is also wide agreement about some other things (which people...")
- 22:28, 24 February 2020 (diff | hist) . . (+323) . . N Deconfusion (Created page with "'''Deconfusion''' is a type of research aimed at making ourselves less confused about fundamental things. ==History=== The term was invented/popularized by MIRI. It was orig...")
- 10:19, 24 February 2020 (diff | hist) . . (+53) . . N MIRI (Redirected page to Machine Intelligence Research Institute) (current) (Tag: New redirect)
- 09:46, 24 February 2020 (diff | hist) . . (+306) . . N The Uncertain Future (Created page with "'''The Uncertain Future''' is a future modeling web applet created by MIRI. Instructions for running it in 2020: https://gist.github.com/riceissa/6e239e8828cceeed5a0bd656...")
- 02:40, 24 February 2020 (diff | hist) . . (+94) . . N List of technical AI alignment agendas (Created page with "This is a '''list of technical AI alignment agendas'''. https://aiwatch.issarice.com/#agendas")
- 00:37, 24 February 2020 (diff | hist) . . (+492) . . N Rapid capability gain vs AGI progress (Created page with "* rapid capability gain seems to refer to how well a ''single'' AI system improves over time, e.g. AlphaGo going from "no knowledge of anything" to "superhuman at Go"...")
- 23:24, 23 February 2020 (diff | hist) . . (+276) . . N Jessica Taylor (Created page with "The most important posts for AI strategy are: * [https://agentfoundations.org/item?id=1220 On motivations for MIRI's highly reliable agent design research] * [https://agentfo...")
- 23:19, 23 February 2020 (diff | hist) . . (+5,066) . . N List of disagreements in AI safety (Created page with "* list of things people disagree about:<ref>[https://drive.google.com/file/d/1wI21XP-lRa6mi5h0dq_USooz0LpysdhS/view Clarifying some key hypotheses in AI alignment].</ref> ** h...")
- 09:43, 23 February 2020 (diff | hist) . . (+43) . . N Simple core algorithm (Redirected page to Secret sauce for intelligence) (current) (Tag: New redirect)
- 09:29, 23 February 2020 (diff | hist) . . (+651) . . N Prosaic AI (Created page with "what are the possibilities for prosaic AI? i.e. if prosaic AI happened, then what are some possible reasons for why this happened? some ideas: * optimizing hard enough produc...")
- 05:06, 23 February 2020 (diff | hist) . . (+28) . . N Goal inference (Redirected page to Value learning) (current) (Tag: New redirect)
- 05:05, 23 February 2020 (diff | hist) . . (+119) . . N Value learning (Created page with "kinds of value learning: * ambitious value learning * narrow value learning ** paul's definition ** rohin's definition")
- 04:52, 23 February 2020 (diff | hist) . . (+550) . . N Human safety problem (Created page with " e.g. "Think of the human as a really badly designed AI with a convoluted architecture that nobody understands, spaghetti code, full of security holes, has no idea what its te...")
- 03:08, 23 February 2020 (diff | hist) . . (+21) . . N AlphaGo Zero (Redirected page to AlphaGo) (current) (Tag: New redirect)
- 02:30, 23 February 2020 (diff | hist) . . (+966) . . N Will there be significant changes to the world prior to some critical AI capability threshold being reached? (Created page with "'''Will there be significant changes to the world prior to some critical AI capability threshold being reached?''' This is currently one of the questions I am most confused ab...")
- 23:25, 22 February 2020 (diff | hist) . . (+23) . . N Evolution analogy (Issa moved page Evolution analogy to Evolution) (current) (Tag: New redirect)
- 23:23, 22 February 2020 (diff | hist) . . (+240) . . N Evolution (Created page with "In discussions of AI risk, evolution is often used as an analogy for the development of AGI. here are some examples: * chimpanzee vs human intelligence * optimization daemo...")
(newest | oldest) View (newer 50 | older 50) (20 | 50 | 100 | 250 | 500)