User contributions
(newest | oldest) View (newer 100 | older 100) (20 | 50 | 100 | 250 | 500)
- 01:35, 22 May 2020 (diff | hist) . . (+75) . . Spaced repetition allows graceful deprecation of experiments
- 01:34, 22 May 2020 (diff | hist) . . (+65) . . N Incremental reading (Created page with "* Incremental reading in Anki Category:Spaced repetition")
- 01:34, 22 May 2020 (diff | hist) . . (+506) . . N Spaced repetition allows graceful deprecation of experiments (Created page with "e.g. my cloze deletion "read only" cards weren't so useful and i eventually switched to a dedicated incremental reading deck. but i can still keep reviewing my old cloze c...")
- 23:28, 21 May 2020 (diff | hist) . . (+56) . . Secret sauce for intelligence (→Evidence)
- 23:12, 21 May 2020 (diff | hist) . . (+51) . . Secret sauce for intelligence
- 22:39, 21 May 2020 (diff | hist) . . (+238) . . List of breakthroughs plausibly needed for AGI
- 22:01, 21 May 2020 (diff | hist) . . (+575) . . There is pressure to rush into a technical agenda
- 21:56, 21 May 2020 (diff | hist) . . (+31) . . List of breakthroughs plausibly needed for AGI
- 21:55, 21 May 2020 (diff | hist) . . (+119) . . List of breakthroughs plausibly needed for AGI
- 21:55, 21 May 2020 (diff | hist) . . (+327) . . N List of breakthroughs plausibly needed for AGI (Created page with "* Looking at things like ''The MIT Encyclopedia of the Cognitive Sciences'' and Judea Pearl's work on causality and trying to estimate how many insights are required to build...")
- 21:55, 21 May 2020 (diff | hist) . . (-251) . . Secret sauce for intelligence (→Evidence)
- 06:18, 21 May 2020 (diff | hist) . . (-3) . . The Hour I First Believed (→Analysis) (current)
- 05:56, 21 May 2020 (diff | hist) . . (+697) . . The Hour I First Believed (HT louis)
- 00:41, 21 May 2020 (diff | hist) . . (+288) . . N Intra-personal comparison test (Created page with "The '''intra-personal comparison test''' is a test of people watching skill. The test asks: given two pieces of work of varying quality produced by a single individual, ca...") (current)
- 00:39, 21 May 2020 (diff | hist) . . (+15) . . Inter-personal comparison test
- 00:38, 21 May 2020 (diff | hist) . . (+273) . . N Inter-personal comparison test (Created page with "The '''inter-personal comparison test''' is a test of people watching skill. Given two people who are superficially similar but in fact very different in quality, can some...")
- 00:37, 21 May 2020 (diff | hist) . . (+76) . . People watching (→Insights/red pills)
- 00:31, 21 May 2020 (diff | hist) . . (+42) . . N People are bad (Created page with "people are bad, mayne Category:Truths") (current)
- 00:30, 21 May 2020 (diff | hist) . . (+19) . . People watching (→Insights/red pills)
- 19:05, 20 May 2020 (diff | hist) . . (+179) . . List of disagreements in AI safety (→Takeoff dynamics)
- 09:41, 20 May 2020 (diff | hist) . . (+80) . . List of disagreements in AI safety (→Takeoff dynamics)
- 09:41, 20 May 2020 (diff | hist) . . (+70) . . Secret sauce for intelligence (→See also)
- 09:41, 20 May 2020 (diff | hist) . . (+573) . . N Secret sauce for intelligence vs specialization in intelligence (Created page with "what is the relationship between the "you can't specialize in 'intelligence'" argument and "there are a small number of insights for AGI" (a.k.a. secret sauce for intelligen...")
- 09:36, 20 May 2020 (diff | hist) . . (+4) . . List of disagreements in AI safety (→Takeoff dynamics)
- 09:36, 20 May 2020 (diff | hist) . . (+33) . . List of disagreements in AI safety (→Takeoff dynamics)
- 09:28, 20 May 2020 (diff | hist) . . (+143) . . Kasparov window
- 09:27, 20 May 2020 (diff | hist) . . (0) . . m Kasparov window (Issa moved page Kasparov Window to Kasparov window over redirect)
- 09:27, 20 May 2020 (diff | hist) . . (+29) . . N Kasparov Window (Issa moved page Kasparov Window to Kasparov window over redirect) (current) (Tag: New redirect)
- 09:17, 20 May 2020 (diff | hist) . . (-3) . . Science argument
- 09:17, 20 May 2020 (diff | hist) . . (-638) . . Secret sauce for intelligence (→Evidence)
- 09:17, 20 May 2020 (diff | hist) . . (+696) . . N Science argument (Created page with "The '''science argument''' says that science is this general "architectural insight" which allowed humans to have much more control over the world, and that w...")
- 08:00, 20 May 2020 (diff | hist) . . (+49) . . Architecture
- 07:59, 20 May 2020 (diff | hist) . . (+229) . . N Content sharing between AIs (Created page with "Part of the discussion about content vs architecture. some common points that get brought up: * content sharing is common in software engineering in general * conten...") (current)
- 07:45, 20 May 2020 (diff | hist) . . (+200) . . List of disagreements in AI safety (→Takeoff dynamics)
- 07:27, 20 May 2020 (diff | hist) . . (+448) . . N List of thought experiments in AI safety (Created page with "list of thought experiments: * dropping seed AGI into world without AGI; see Counterfactual of dropping a seed AI into a world without other capable AI * the analogy of t...") (current)
- 05:31, 20 May 2020 (diff | hist) . . (+66) . . List of disagreements in AI safety (→Machine learning safety)
- 05:14, 20 May 2020 (diff | hist) . . (+260) . . People watching (→Insights/red pills)
- 05:07, 20 May 2020 (diff | hist) . . (+91) . . People watching (→Techniques)
- 04:52, 20 May 2020 (diff | hist) . . (-46) . . List of disagreements in AI safety (→See also)
- 04:52, 20 May 2020 (diff | hist) . . (+54) . . List of disagreements in AI safety (→Machine learning safety)
- 04:52, 20 May 2020 (diff | hist) . . (+54) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 01:36, 20 May 2020 (diff | hist) . . (+59) . . Mass shift to technical AI safety research is suspicious
- 01:36, 20 May 2020 (diff | hist) . . (+9) . . Mass shift to technical AI safety research is suspicious
- 01:35, 20 May 2020 (diff | hist) . . (+51) . . Mass shift to technical AI safety research is suspicious
- 01:35, 20 May 2020 (diff | hist) . . (+152) . . Mass shift to technical AI safety research is suspicious
- 01:34, 20 May 2020 (diff | hist) . . (+78) . . There is pressure to rush into a technical agenda
- 01:33, 20 May 2020 (diff | hist) . . (+620) . . N Mass shift to technical AI safety research is suspicious (Created page with "Back in 2008-2011 when people were talking about AI safety on LessWrong, there were multiple "singularity strategies" that were proposed, of which technical AI safety was...")
- 01:30, 20 May 2020 (diff | hist) . . (+63) . . My current thoughts on the technical AI safety pipeline (outside academia) (current)
- 00:57, 20 May 2020 (diff | hist) . . (+220) . . AI safety technical pipeline does not teach how to start having novel thoughts
- 02:15, 19 May 2020 (diff | hist) . . (+105) . . Ongoing friendship and collaboration is important
- 02:13, 19 May 2020 (diff | hist) . . (+16) . . Ongoing friendship and collaboration is important
- 02:13, 19 May 2020 (diff | hist) . . (+159) . . Ongoing friendship and collaboration is important
- 02:10, 19 May 2020 (diff | hist) . . (+19) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 02:10, 19 May 2020 (diff | hist) . . (0) . . m Giving advice in response to generic questions is difficult but important (Issa moved page Generic advice is difficult to give but also important to Giving advice in response to generic questions is difficult but important)
- 02:10, 19 May 2020 (diff | hist) . . (+87) . . N Generic advice is difficult to give but also important (Issa moved page Generic advice is difficult to give but also important to Giving advice in response to generic questions is difficult but important) (current) (Tag: New redirect)
- 01:51, 19 May 2020 (diff | hist) . . (+157) . . It is difficult to get feedback on published work
- 01:47, 19 May 2020 (diff | hist) . . (+1) . . Ongoing friendship and collaboration is important
- 00:30, 19 May 2020 (diff | hist) . . (+194) . . Ongoing friendship and collaboration is important
- 00:29, 19 May 2020 (diff | hist) . . (+56) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 00:29, 19 May 2020 (diff | hist) . . (+275) . . N Ongoing friendship and collaboration is important (Created page with "Ongoing friendship and collaboration is to be contrasted with one-off replies you might get from people if you post something. I think of of the reasons that AI safety is n...")
- 00:26, 19 May 2020 (diff | hist) . . (+322) . . It is difficult to get feedback on published work
- 00:25, 19 May 2020 (diff | hist) . . (+75) . . It is difficult to get feedback on published work
- 00:25, 19 May 2020 (diff | hist) . . (+71) . . It is difficult to find people to bounce ideas off of
- 00:24, 19 May 2020 (diff | hist) . . (+383) . . There is room for something like RAISE
- 00:22, 19 May 2020 (diff | hist) . . (+47) . . There is room for something like RAISE
- 00:20, 19 May 2020 (diff | hist) . . (+646) . . There is room for something like RAISE
- 00:16, 19 May 2020 (diff | hist) . . (+56) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 00:16, 19 May 2020 (diff | hist) . . (+29) . . N It is difficult to get feedback on published work (Created page with " Category:AI safety meta")
- 23:30, 18 May 2020 (diff | hist) . . (+60) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 23:30, 18 May 2020 (diff | hist) . . (+98) . . N It is difficult to find people to bounce ideas off of (Created page with "The people who can give the most useful feedback tend to be very busy Category:AI safety meta")
- 23:25, 18 May 2020 (diff | hist) . . (+178) . . Nobody understands what makes people snap into AI safety
- 23:24, 18 May 2020 (diff | hist) . . (+62) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 23:24, 18 May 2020 (diff | hist) . . (+1,177) . . N Newcomers in AI safety are silent about their struggles (Created page with "It's actually pretty hard to find people openly complaining about how to get involved in AI safety. You can find some random comments, and there are occasional Facebook thread...")
- 23:18, 18 May 2020 (diff | hist) . . (+344) . . The Secret of Psalm 46
- 23:06, 18 May 2020 (diff | hist) . . (+180) . . Giving advice in response to generic questions is difficult but important
- 23:05, 18 May 2020 (diff | hist) . . (+2) . . Giving advice in response to generic questions is difficult but important
- 23:05, 18 May 2020 (diff | hist) . . (+61) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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...")
- 22:58, 18 May 2020 (diff | hist) . . (+135) . . AI safety is harder than most things
- 22:50, 18 May 2020 (diff | hist) . . (+31) . . AI safety is harder than most things
- 22:49, 18 May 2020 (diff | hist) . . (+336) . . AI safety is harder than most things
- 22:46, 18 May 2020 (diff | hist) . . (+24) . . AI safety is harder than most things
- 22:46, 18 May 2020 (diff | hist) . . (+137) . . AI safety lacks a space to ask stupid or ballsy questions
- 22:00, 18 May 2020 (diff | hist) . . (+96) . . Nobody understands what makes people snap into AI safety
- 21:56, 18 May 2020 (diff | hist) . . (+13) . . The Secret of Psalm 46
- 21:56, 18 May 2020 (diff | hist) . . (+55) . . The Secret of Psalm 46
- 21:55, 18 May 2020 (diff | hist) . . (+109) . . Nobody understands what makes people snap into AI safety
- 21:53, 18 May 2020 (diff | hist) . . (+84) . . Nobody understands what makes people snap into AI safety
- 21:53, 18 May 2020 (diff | hist) . . (+74) . . Nobody understands what makes people snap into AI safety
- 21:52, 18 May 2020 (diff | hist) . . (+60) . . Nobody understands what makes people snap into AI safety
- 21:51, 18 May 2020 (diff | hist) . . (+63) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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...")
- 21:43, 18 May 2020 (diff | hist) . . (+147) . . AI safety is harder than most things
- 21:41, 18 May 2020 (diff | hist) . . (+43) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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...")
- 21:34, 18 May 2020 (diff | hist) . . (+24) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 21:33, 18 May 2020 (diff | hist) . . (+60) . . My take on RAISE (current)
- 21:33, 18 May 2020 (diff | hist) . . (+57) . . There is room for something like RAISE
- 21:33, 18 May 2020 (diff | hist) . . (+19) . . My take on RAISE
- 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...")
(newest | oldest) View (newer 100 | older 100) (20 | 50 | 100 | 250 | 500)