Search results

Create the page "Question" on this wiki! See also the search results found.

Page title matches

• Desiderata for dissolving the question
  ...n or world actually works, i.e. either answer the question or dissolve the question. For free will, this would be explaining how the world is deterministic but ...ction". So this page should probably called "desiderata for dissolving the question".] Explain the cognitive cause of the original error. For free will, this w
  6 KB (973 words) - 21:06, 30 July 2021
• Online question-answering services are unreliable
  ...rk around half of the time (when the question text is high quality and the question is submitted to the most promising venue). * [[Unreliability of online question-answering services makes it emotionally taxing to write up questions]]
  1 KB (159 words) - 02:36, 28 March 2021
• Unreliability of online question-answering services makes it emotionally taxing to write up questions
  ...ay off. This feeling of uncertainty, that I could spend time writing up my question only to be completely ignored, is one of the big reasons why I don't post m
  428 bytes (69 words) - 02:39, 28 March 2021

Page text matches

• List of timelines for futuristic technologies
  there's also the question of relative vs absolute timelines. given all the "game-changing technologie
  871 bytes (119 words) - 01:01, 26 March 2021
• Different senses of claims about AGI
  ...ality of "ideal" agents help us build AI systems that we understand well? (question is (2) in [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-abo
  1 KB (212 words) - 22:14, 28 April 2020
• Simple core of consequentialist reasoning
  ...ings you weren't specifically programmed for". this isn't exactly the same question though; it's possible to have general intelligence, but where this general
  1 KB (217 words) - 19:11, 27 February 2021
• Analyzing disagreements
  ...simple question of fact, it should appear one-sided, but if it's a policy question with multiple parties who have different stakes and each policy affects peo
  7 KB (1,087 words) - 22:52, 8 February 2021
• How doomed are ML safety approaches?
  an important question for me is something like, if paul's approach doesn't work, how would we fin [[Category:Question]]
  5 KB (765 words) - 02:32, 28 March 2021
• My understanding of how IDA works
  ...hand'', so the amplified system is itself completely automatic. So then my question becomes something like, if the number of samples is the problem, then why d
  9 KB (1,597 words) - 00:27, 6 October 2020
• Minimal AGI vs task AGI
  see my question here: https://www.greaterwrong.com/posts/hL9ennoEfJXMj7r2D/two-clarificatio
  770 bytes (115 words) - 19:10, 27 February 2021
• Counterfactual of dropping a seed AI into a world without other capable AI
  ...agent were teleported into today's world, could it take over?" versus the question of "Who develops it, in what order, and were they all trading insights or w
  3 KB (426 words) - 20:51, 15 March 2021
• AlphaGo
  | 2016-03-09 || [https://www.facebook.com/yudkowsky/posts/10154009668254228 Question for someone with a much deeper understanding of Go: If a 6p was analyzing a
  5 KB (672 words) - 20:19, 11 August 2021
• Will there be significant changes to the world prior to some critical AI capability threshold being reached?
  [[Category:Question]]
  2 KB (251 words) - 02:40, 28 March 2021
• List of disagreements in AI safety
  ...ons together answer the question. sub-level questions answer the top level question, and so forth. ...nical fields to build intuition). This train of thought led me to ask this question: [https://www.greaterwrong.com/posts/bDwQddhqaTiMhbpPF/what-are-some-exerci
  21 KB (3,254 words) - 11:00, 26 February 2022
• UDASSA
  ...what is the shortest program to output that OM) sways the outcome. So the question is, does it take an extra bit to specify monday vs tuesday in the tails wor
  14 KB (2,432 words) - 09:13, 8 January 2023
• Convergent evolution of values
  ...cing-suffering.org/why-organisms-feel-both-suffering-and-happiness -- this question of why there is both pain and pleasure; if we can answer this one, then we
  8 KB (1,248 words) - 17:50, 9 April 2021
• Interacting with copies of myself
  ...erged and so forth, what kinds of intuitions would i have wrt this kind of question?
  5 KB (842 words) - 20:40, 12 April 2021
• List of men by number of sons, daughters, and wives
  ...e to travel the world. He and Yoko have no children - they were out of the question when the couple were running the jazz club and when he began writing, but M
  29 KB (4,200 words) - 17:21, 2 August 2021
• Statistical analysis of expert timelines argument for AI timelines
  ...elines to come up with some overall estimate of AI timelines. It punts the question of "but where did the experts get their opinions?" to one or more of the ot
  641 bytes (101 words) - 05:10, 9 April 2021
• The Precipice notes
  ...h regulations preventing super crappy housing. i guess this isn't really a question.
  3 KB (565 words) - 00:23, 27 April 2020
• Linked list proof card
  ...hen writing the proof, you can make a "small" card that answers a specific question). — maybe another way to state this is that you don't ''need'' random acc
  3 KB (620 words) - 01:06, 17 July 2021
• Incremental reading in Anki
  * Always include question side when replaying audio: yes
  4 KB (687 words) - 01:10, 17 July 2021
• Reverse side card for everything
  ...ll the idea, but also the term itself (so you can use the term). For every question, you want to play a version of Jeopardy. "Every thought has a counterpart/d
  2 KB (300 words) - 00:41, 19 August 2023
• Encoding dependence problem
  ...to get to that you still need to first learn the encodings. But then, the question is, how do you deal with this in Anki, especially if you work with multiple
  1 KB (214 words) - 20:02, 14 May 2021
• Desiderata for dissolving the question
  ...n or world actually works, i.e. either answer the question or dissolve the question. For free will, this would be explaining how the world is deterministic but ...ction". So this page should probably called "desiderata for dissolving the question".] Explain the cognitive cause of the original error. For free will, this w
  6 KB (973 words) - 21:06, 30 July 2021
• Architecture
  ...ttps://intelligence.org/files/AIFoomDebate.pdf#page=559] -- Right, the key question is quantitative: exactly how much initial content (in bytes or some other u ...ans and chimpanzees mostly about architecture or content? there's also the question of humans now vs humans thousands of years ago, where it seems clear that t
  7 KB (1,128 words) - 23:18, 23 June 2020
• Competence gap
  Maybe another question to ask, or possibly an equivalent phrasing, is "will AIs be doing most of t
  3 KB (477 words) - 00:01, 30 May 2020
• Spoiler test of depth
  ...to read spoilers before watching a movie/reading a book" (i.e. the related question of whether one would like to hear spoilers before consuming a story). (If y
  4 KB (672 words) - 22:18, 3 August 2020
• The mathematics community has no clear standards for what a mathematician should know
  ...rcher, how well should i understand analysis/linear algebra/etc? this is a question many people would ask, i think.
  1 KB (209 words) - 01:03, 17 July 2021
• Choosing problems for spaced proof review
  I think it's an open question to me how to decide which problems to review in spaced proof review, or e.g
  3 KB (466 words) - 23:46, 22 May 2020
• Deck options for proof cards
  * Always include question side when replaying audio: yes
  2 KB (318 words) - 01:09, 17 July 2021
• Flag things to fix during review
  ...ross some incongruity or question while reviewing a card, i write down the question on the paper in front of me (i always have a scratch paper in front of me f then, after finishing my daily reviews, i go back to each question and i make new cards about them.
  1 KB (198 words) - 02:32, 28 March 2021
• There is room for something like RAISE
  ...uestion-answering services are unreliable]], and [[Unreliability of online question-answering services makes it emotionally taxing to write up questions|this u
  3 KB (447 words) - 18:34, 18 July 2021
• Nobody understands what makes people snap into AI safety
  ...g their full-time attention on AI safety? I think this is a very important question, and I don't think anybody understands this well. For example, in 2016 I do
  2 KB (268 words) - 02:35, 28 March 2021
• Ongoing friendship and collaboration is important
  ...e reliable than [[Online question-answering services are unreliable|online question-answering services]].
  1 KB (195 words) - 02:35, 28 March 2021
• Goalpost for usefulness of HRAD work
  When thinking about the question of "How useful is [[HRAD]] work?", what standards/goalposts should we use? It seems like there's a question of what is the relevant goalpost, for deciding whether HRAD work is useful.
  3 KB (480 words) - 20:17, 26 June 2020
• Online question-answering services are unreliable
  ...rk around half of the time (when the question text is high quality and the question is submitted to the most promising venue). * [[Unreliability of online question-answering services makes it emotionally taxing to write up questions]]
  1 KB (159 words) - 02:36, 28 March 2021
• Unreliability of online question-answering services makes it emotionally taxing to write up questions
  ...ay off. This feeling of uncertainty, that I could spend time writing up my question only to be completely ignored, is one of the big reasons why I don't post m
  428 bytes (69 words) - 02:39, 28 March 2021
• AI timelines
  '''AI timelines''' refers to the question of when we will see advanced AI technology.
  691 bytes (93 words) - 01:36, 5 April 2021
• Missing gear for intelligence
  ...y would suggest... But you could have whole journal issues about that one question, so I'm just going to leave it at that."<ref>https://lw2.issarice.com/posts
  8 KB (1,275 words) - 21:42, 30 June 2020
• AlphaGo as evidence of discontinuous takeoff
  lw question: was there a discontinuity in Go capability within deepmind itself? if so, ...ations do ML systems go through before they make it out to the world? this question matters mostly for AI systems that produce a large qualitative shift in how
  3 KB (456 words) - 23:35, 2 August 2022
• List of AI safety projects I could work on
  * Ask lots of questions on LW, e.g.: (duration tier depends on question; I believe I can rush through and ask certain questions within an hour whic
  6 KB (927 words) - 14:25, 4 February 2022
• How meta should AI safety be?
  [[Category:Question]]
  873 bytes (144 words) - 02:33, 28 March 2021
• Will it be possible for humans to detect an existential win?
  [[Category:Question]]
  691 bytes (115 words) - 02:40, 28 March 2021
• Asynchronous support
  ...you come across one that was written years ago and comment on it asking a question, you are pretty unlikely to get a reply.
  831 bytes (134 words) - 19:28, 3 October 2021
• Learning-complete
  ...at you could learn a lot of math/econ/physics/whatever just by asking this question repeatedly and solving these problems. Especially if the model can take int ...g/watching lectures. so i think "easiest problem you can't solve" is one, "question oracle" is another, etc.
  3 KB (452 words) - 05:02, 16 July 2021
• Expert response heuristic for prompt writing
  ...that sometimes happens in talks where the lecturer will ask the audience a question, and the audience sometimes gives good thoughts but the lecturer is looking
  3 KB (560 words) - 00:52, 17 July 2021
• Add all permutations of a card to prevent pattern-matching
  ...would work in a case like that. I think you'd need to convert it to basic question-answer cards.
  2 KB (365 words) - 07:26, 18 August 2023
• Is AI safety no longer a scenius?
  [[Category:Question]]
  2 KB (337 words) - 02:34, 28 March 2021
• What would a vow of silence look like for math?
  [[Category:Question]]
  575 bytes (89 words) - 01:00, 17 July 2021
• Tutoring heuristic for prompt writing
  ...ugh prompts (and possibly [[integration card]]s) to be prepared for such a question. So you can think of the back side of a card (or collection of cards) as wh
  1 KB (217 words) - 18:29, 18 July 2021
• Can spaced repetition interfere with internal sense of relevance?
  [[Category:Question]]
  2 KB (284 words) - 01:54, 16 August 2023
• Optimal unlocking mechanism for booster cards is unclear
  ...latter case, there is the further [[Should booster cards be marked as new?|question]] of whether to make booster cards visually distinct from existing cards).
  2 KB (335 words) - 00:57, 17 July 2021

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