User contributions
(newest | oldest) View (newer 50 | older 50) (20 | 50 | 100 | 250 | 500)
- 23:05, 18 May 2020 (diff | hist) . . (+825) . . N Giving advice in response to generic questions is difficult but important (Created page with "I've seen a few times people saying things like "Don't contact me with generic questions like 'What should I work on?' because I can't help you. I can answer more straightforw...")
- 21:51, 18 May 2020 (diff | hist) . . (+1,008) . . N Nobody understands what makes people snap into AI safety (Created page with "Getting even slightly interested in AI safety is hard. You need to have a mind that can understand other important things like cryonics/anti-aging, Tegmark multiverse, con...")
- 21:41, 18 May 2020 (diff | hist) . . (+464) . . N AI safety is harder than most things (Created page with "I recently got a visceral sense that '''AI safety is harder than most things''' when I started writing my [https://taoanalysis.wordpress.com/ Tao Analysis Solutions] blog. Aft...")
- 21:32, 18 May 2020 (diff | hist) . . (+1,219) . . N My take on RAISE (Created page with "From October 2018: * I'm generally optimistic about making things easier to understand/distilling things. So I like this general area that RAISE is working in. * I'm not sure...")
- 21:21, 18 May 2020 (diff | hist) . . (+96) . . N Timeline of my involvement in AI safety (Created page with "{| class="sortable wikitable" |- ! Year !! Month !! Event |- | a |} Category:AI safety meta")
- 21:10, 18 May 2020 (diff | hist) . . (+904) . . N AI safety lacks a space to ask stupid or ballsy questions (Created page with "(this page assumes that asking stupid or ballsy questions is important for learning/making intellectual progress) I think the way that voting and crossposting work on LessW...")
- 20:59, 18 May 2020 (diff | hist) . . (+2,098) . . N There is pressure to rush into a technical agenda (Created page with "AI safety has a weird dynamic going on where: * Most likely, only a single technical agenda will actually be useful. The others will have been good in expectation (in like a...")
- 20:38, 18 May 2020 (diff | hist) . . (+866) . . N Mixed messaging regarding independent thinking (Created page with "I think the AI safety community and effective altruism in general has some mixed messaging going on regarding whether it's good to be an "independent thinker". On one...") (current)
- 20:30, 18 May 2020 (diff | hist) . . (+321) . . N AI safety is not a community (Created page with "When I am feeling especially cynical and upset, it feels like '''AI safety is not a community'''. What do I mean by this? Basically, I think I've been in communities before, a...")
- 20:23, 18 May 2020 (diff | hist) . . (+319) . . N AI safety technical pipeline does not teach how to start having novel thoughts (Created page with "Currently, the AI safety community does not have an explicit mechanism for teaching new people how to start having novel thoughts. The implicit hope seems to be something...")
- 20:11, 18 May 2020 (diff | hist) . . (+71) . . N Category:AI safety meta (Created page with "For thoughts about the AI safety community and doing work in AI safety.") (current)
- 20:06, 18 May 2020 (diff | hist) . . (+73) . . N My current thoughts on the technical AI safety pipeline (outside academia) (Created page with "* There is room for something like RAISE Category:AI safety meta")
- 20:05, 18 May 2020 (diff | hist) . . (+365) . . N There is room for something like RAISE (Created page with "Self-studying all of the technical prerequisites for technical AI safety research is hard. The most that people new to the field get are a list of textbooks. I think there...")
- 01:10, 18 May 2020 (diff | hist) . . (+61) . . N Intelligence amplification (Created page with "https://nickbostrom.com/cognitive.pdf Category:AI safety") (current)
- 01:06, 18 May 2020 (diff | hist) . . (+876) . . N List of critiques of iterated amplification (Created page with ""critique" in the sense of "specific objection" not "piece of writing containing multiple objections" places to look: * https://intelligence.org/2018/05/19/challenges-to-chr...")
- 00:19, 17 May 2020 (diff | hist) . . (+57) . . N Using Anki for math (Created page with " Spaced proof review Category:Spaced repetition")
- 21:51, 16 May 2020 (diff | hist) . . (+67) . . N Slow feedback cycle for spaced repetition (Redirected page to Spaced repetition experiments take months to complete) (current) (Tag: New redirect)
- 21:51, 16 May 2020 (diff | hist) . . (+67) . . N Slow feedback loop for spaced repetition (Redirected page to Spaced repetition experiments take months to complete) (current) (Tag: New redirect)
- 21:42, 16 May 2020 (diff | hist) . . (+843) . . N Flag things to fix during review (Created page with "one thing i do while doing my daily reviews: if i come across some incongruity or question while reviewing a card, i write down the question on the paper in front of me (i alw...")
- 08:53, 16 May 2020 (diff | hist) . . (+34) . . N Parasitizing on popularity (Issa moved page Parasitizing on popularity to Popularity symbiosis) (current) (Tag: New redirect)
- 00:50, 16 May 2020 (diff | hist) . . (+184) . . N Category:Learning (Created page with "This is for pages that should probably go on the Learning Subwiki but they are too opinionated as written, and should probably be toned down/rewritten in a more encyclopedic w...")
- 00:48, 16 May 2020 (diff | hist) . . (+325) . . N Feynman technique fails when existing explanations are bad (Created page with "The [https://learning.subwiki.org/wiki/Feynman_technique Feynman technique] is great when you really want to internalize something. But the technique has a problem when all ex...")
- 00:24, 16 May 2020 (diff | hist) . . (+876) . . N Spaced repetition prevents unrecalled unrecallables (Created page with "In analogy with the known unknowns vs unknown unknowns distinction, we might distinguish between the following: * recalled unrecallables: things that you are aware you can't...")
- 23:50, 15 May 2020 (diff | hist) . . (+942) . . N Dealing with bad problems in spaced proof review (Created page with "Choosing the right problems is important if you want to make spaced proof review a habit. But what if you've added a bad prob...")
- 23:45, 15 May 2020 (diff | hist) . . (+536) . . N Choosing problems for spaced proof review (Created page with "Spaced proof review takes a lot of effort to implement even if done correctly. One of the mistakes one can make is to choose problems which aren't worth solving over and o...")
- 22:20, 15 May 2020 (diff | hist) . . (+26) . . N Fake review (Redirected page to Empty review) (current) (Tag: New redirect)
- 22:20, 15 May 2020 (diff | hist) . . (+346) . . N Empty review (Created page with "An '''empty review''' or '''fake review''' is a review of a card in Anki where you just press "Good" without thinking it through. This is most useful when reviewing big...")
- 07:19, 15 May 2020 (diff | hist) . . (+887) . . N Spaced proof review is not about memorizing proofs (Created page with "Spaced proof review involves proving a result at spaced intervals with the help of Anki. And Anki is about memorizing things. So at first glance, it seems like the goa...")
- 06:42, 15 May 2020 (diff | hist) . . (+1,021) . . N Use paper during spaced repetition reviews (Created page with "People like to talk about how they review their Anki cards while waiting in line or on their bus rides or whatever, but a core feature of how I review my Anki cards is to...")
- 04:02, 15 May 2020 (diff | hist) . . (+697) . . N Spaced repetition experiments take months to complete (Created page with "By the very nature of spaced repetition, any experiment that tries to test some aspect of it will take months to complete. This is because in order to see how much you remembe...")
- 03:41, 15 May 2020 (diff | hist) . . (+1,504) . . N Bury effortful cards to speed up review (Created page with "A spaced repetition deck has cards varying in difficulty. One problem you might have is that because there are these more effortful cards, you might be tempted to skip reviewi...")
- 03:17, 15 May 2020 (diff | hist) . . (+547) . . N Add the complete proof on proof cards to reduce friction when reviewing (Created page with "i also now think that putting the full solution on the card, rather than just a reference to a textbook or web page, is better. it keeps everything self-contained, so when you...")
- 02:47, 15 May 2020 (diff | hist) . . (+701) . . N Spaced proof review routine (Created page with "Here are the basic steps I take for spaced proof review. For each proof/exercise: # Do the proof for the first time. This isn't any different from what people normally d...")
- 02:41, 15 May 2020 (diff | hist) . . (+833) . . N Do an empty review of proof cards immediately after adding to prevent backlog (Created page with "Proof cards are big, so you probably have a limit to new cards per day (maybe 1-5). This means if you solve a bunch of exercises on a day, you can add more cards...")
- 02:06, 15 May 2020 (diff | hist) . . (+1,220) . . N Why ain'tcha better at math (Created page with "I feel like one response people might have, if they hear that I think I have new and exciting way to learn math, is to ask why I personally am not the best at math. There are...")
- 01:40, 15 May 2020 (diff | hist) . . (+676) . . N Managing micro-movements in learning (Created page with "(there must be a better term for this...) * Some math books are good at putting things like "(why?)" to mark non-trivial inferential steps. This is comforting especially at a...")
- 01:32, 15 May 2020 (diff | hist) . . (+745) . . N Deck options for proof cards (Created page with "Here are my deck options (as of 2020-05-14) for my proof cards decks. New Cards: * Steps: 960 * Order: Show new cards in order added * New cards/day: 1 * Graduating interval...")
- 01:11, 15 May 2020 (diff | hist) . . (+199) . . N Big card (Created page with "A '''big card''' is an Anki card that takes a long time to review (say, longer than 1 minute). This is in contrast to small cards which can be reviewed in a small amou...")
- 01:00, 15 May 2020 (diff | hist) . . (+1,127) . . N The mathematics community has no clear standards for what a mathematician should know (Created page with "mathematicians suck at communicating the differences between (1) stuff you should work through in detail once, but then forget about it later; (2) stuff you should know super...")
- 00:54, 15 May 2020 (diff | hist) . . (+749) . . N Discursive texts are difficult to ankify (Created page with "[https://learning.subwiki.org/wiki/Discursiveness_(explanations) Discursive]/meandering texts reference topics outside of the main one, going off in tangents. While this can m...")
- 00:49, 15 May 2020 (diff | hist) . . (+811) . . N Quotability vs ankifiability (Created page with "Something is '''quotable''' if it is easy to make into a quote. As someone who has [https://en.wikiquote.org/wiki/Special:Contributions/Riceissa written] a bunch of Wikiquote...")
- 20:48, 10 May 2020 (diff | hist) . . (+194) . . N Spoiler test of depth (Created page with "The '''spoiler test of depth''' states that if something can be "spoiled" by spoilers, then it isn't deep, or in other words, that truly deep things cannot be spoiled by givin...")
- 09:50, 6 May 2020 (diff | hist) . . (+35) . . N WBE (Redirected page to Whole brain emulation) (current) (Tag: New redirect)
- 05:45, 6 May 2020 (diff | hist) . . (+79) . . N Discontinuities in whole brain emulation technology (Issa moved page Discontinuities in whole brain emulation technology to Discontinuities in usefulness of whole brain emulation technology) (current) (Tag: New redirect)
- 05:39, 6 May 2020 (diff | hist) . . (+770) . . N Discontinuities in usefulness of whole brain emulation technology (Created page with "Even Robin Hanson admits that whole brain emulations would result in a foom-ish/local outcome: """Eliezer: Right. So, in other words, we get a centralized economic shock,...")
- 05:31, 6 May 2020 (diff | hist) . . (+1,021) . . N One wrong number problem (Created page with "The '''one wrong number problem''' has been discussed by Eliezer Yudkowsky in at least two contexts: * To talk about complexity of human values: "But suppose one or more...")
- 01:42, 1 May 2020 (diff | hist) . . (+2,286) . . N 3Blue1Brown (Created page with "Here's my current (April 2020) views on 3Blue1Brown's math videos: * he puts in a lot of effort into the visualizations, so they look pretty. these visualizations are actuall...")
- 18:54, 29 April 2020 (diff | hist) . . (+111) . . N Architecture (Created page with "What is meant by terms like "mental architecture", "cognitive architecture", the "architecture of the AI", etc?")
- 22:55, 28 April 2020 (diff | hist) . . (+5,113) . . N Desiderata for dissolving the question (Created page with "* I think when most people think about philosophy topics, they just stop thinking about it once they no longer feel confused? Like, they don't start out with a bunch of deside...")
- 21:28, 28 April 2020 (diff | hist) . . (+420) . . N Richard Ngo (Created page with "'''Richard Ngo''' is an AI safety research engineer at Google DeepMind.<ref>[https://forum.effectivealtruism.org/users/richard_ngo richard_ngo]. "AI safety research engin...")
(newest | oldest) View (newer 50 | older 50) (20 | 50 | 100 | 250 | 500)