User contributions
(newest | oldest) View (newer 250 | older 250) (20 | 50 | 100 | 250 | 500)
- 06:25, 3 June 2020 (diff | hist) . . (+470) . . Prosaic AI
- 03:42, 3 June 2020 (diff | hist) . . (+10) . . Secret sauce for intelligence (→Evidence)
- 02:58, 3 June 2020 (diff | hist) . . (+61) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 02:56, 3 June 2020 (diff | hist) . . (+45) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 02:53, 3 June 2020 (diff | hist) . . (+69) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 02:40, 3 June 2020 (diff | hist) . . (+430) . . List of success criteria for HRAD work
- 00:56, 3 June 2020 (diff | hist) . . (+22) . . List of success criteria for HRAD work
- 00:56, 3 June 2020 (diff | hist) . . (+216) . . List of success criteria for HRAD work
- 00:46, 3 June 2020 (diff | hist) . . (-2) . . List of success criteria for HRAD work
- 00:41, 3 June 2020 (diff | hist) . . (+266) . . List of success criteria for HRAD work
- 10:08, 2 June 2020 (diff | hist) . . (+590) . . People watching (→Insights/red pills)
- 10:03, 2 June 2020 (diff | hist) . . (+887) . . People watching
- 02:33, 2 June 2020 (diff | hist) . . (+326) . . List of success criteria for HRAD work
- 02:14, 2 June 2020 (diff | hist) . . (+183) . . List of success criteria for HRAD work
- 02:12, 2 June 2020 (diff | hist) . . (+500) . . List of success criteria for HRAD work
- 22:38, 1 June 2020 (diff | hist) . . (+189) . . List of success criteria for HRAD work
- 22:34, 1 June 2020 (diff | hist) . . (+215) . . List of success criteria for HRAD work
- 22:21, 1 June 2020 (diff | hist) . . (+77) . . List of success criteria for HRAD work
- 22:21, 1 June 2020 (diff | hist) . . (+195) . . List of success criteria for HRAD work
- 22:18, 1 June 2020 (diff | hist) . . (+183) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 21:15, 1 June 2020 (diff | hist) . . (+92) . . List of success criteria for HRAD work
- 21:13, 1 June 2020 (diff | hist) . . (+51) . . List of success criteria for HRAD work
- 21:12, 1 June 2020 (diff | hist) . . (+84) . . List of success criteria for HRAD work
- 21:11, 1 June 2020 (diff | hist) . . (+45) . . Goalpost for usefulness of HRAD work (→See also)
- 21:11, 1 June 2020 (diff | hist) . . (+45) . . Something like realism about rationality (→See also)
- 21:11, 1 June 2020 (diff | hist) . . (+129) . . N List of success criteria for HRAD work (Created page with " ==See also== * Something like realism about rationality * Goalpost for usefulness of HRAD work Category:AI safety")
- 23:49, 31 May 2020 (diff | hist) . . (+3) . . Something like realism about rationality (→notes)
- 01:23, 30 May 2020 (diff | hist) . . (+36) . . Hardware argument for AI timelines
- 01:20, 30 May 2020 (diff | hist) . . (+197) . . Hardware argument for AI timelines
- 01:07, 30 May 2020 (diff | hist) . . (+416) . . Hardware argument for AI timelines
- 01:03, 30 May 2020 (diff | hist) . . (+88) . . N AI timelines (Created page with "For now, see List of disagreements in AI safety#AI timelines Category:AI safety")
- 01:02, 30 May 2020 (diff | hist) . . (+977) . . Hardware argument for AI timelines
- 00:01, 30 May 2020 (diff | hist) . . (+476) . . Competence gap (→notes) (current)
- 23:21, 29 May 2020 (diff | hist) . . (+120) . . People watching (→Insights/red pills)
- 23:18, 29 May 2020 (diff | hist) . . (+130) . . People watching (→Techniques)
- 22:44, 29 May 2020 (diff | hist) . . (+798) . . People watching
- 22:39, 29 May 2020 (diff | hist) . . (+176) . . Online question-answering services are unreliable (→See also)
- 22:37, 29 May 2020 (diff | hist) . . (-1) . . Online question-answering services are unreliable
- 22:37, 29 May 2020 (diff | hist) . . (+4) . . Online question-answering services are unreliable
- 22:36, 29 May 2020 (diff | hist) . . (+144) . . Ongoing friendship and collaboration is important
- 22:35, 29 May 2020 (diff | hist) . . (+64) . . There is room for something like RAISE
- 22:34, 29 May 2020 (diff | hist) . . (-63) . . There is room for something like RAISE
- 22:34, 29 May 2020 (diff | hist) . . (+123) . . Online question-answering services are unreliable
- 22:34, 29 May 2020 (diff | hist) . . (+409) . . N Unreliability of online question-answering services makes it emotionally taxing to write up questions (Created page with "Online question-answering services are unreliable, and this unreliability makes it emotionally taxing to write up questions because you aren't sure if the time you spend w...")
- 22:31, 29 May 2020 (diff | hist) . . (-294) . . There is room for something like RAISE
- 22:31, 29 May 2020 (diff | hist) . . (+138) . . Online question-answering services are unreliable
- 22:30, 29 May 2020 (diff | hist) . . (+554) . . N Online question-answering services are unreliable (Created page with "In my experience,<ref>https://math.stackexchange.com/users/35525/riceissa?tab=questions</ref><ref>https://stats.stackexchange.com/users/273265/riceissa?tab=questions</ref><ref...")
- 09:05, 29 May 2020 (diff | hist) . . (+31) . . Secret sauce for intelligence (→Evidence)
- 21:55, 28 May 2020 (diff | hist) . . (+297) . . Competence gap (→notes)
- 19:12, 27 May 2020 (diff | hist) . . (+156) . . Narrow window argument against continuous takeoff
- 09:30, 27 May 2020 (diff | hist) . . (+5) . . Goalpost for usefulness of HRAD work
- 09:30, 27 May 2020 (diff | hist) . . (+6) . . Goalpost for usefulness of HRAD work
- 09:30, 27 May 2020 (diff | hist) . . (+303) . . Goalpost for usefulness of HRAD work
- 09:28, 27 May 2020 (diff | hist) . . (+880) . . Goalpost for usefulness of HRAD work
- 09:24, 27 May 2020 (diff | hist) . . (+484) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 09:19, 27 May 2020 (diff | hist) . . (+13) . . Secret sauce for intelligence
- 09:18, 27 May 2020 (diff | hist) . . (+36) . . Secret sauce for intelligence
- 09:13, 27 May 2020 (diff | hist) . . (+150) . . Science argument
- 09:12, 27 May 2020 (diff | hist) . . (+160) . . Science argument
- 09:00, 27 May 2020 (diff | hist) . . (+22) . . Ignore Anki add-ons to focus on fundamentals
- 08:59, 27 May 2020 (diff | hist) . . (+526) . . N Ignore Anki add-ons to focus on fundamentals (Created page with "There are many add-ons available for Anki. So far I've ignored all of them; never in the past two years have I installed an add-on for Anki. It took me over a year I think...")
- 07:44, 27 May 2020 (diff | hist) . . (-37) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 07:36, 27 May 2020 (diff | hist) . . (+4) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 07:30, 27 May 2020 (diff | hist) . . (+62) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 07:28, 27 May 2020 (diff | hist) . . (+30) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 07:19, 27 May 2020 (diff | hist) . . (+124) . . Goalpost for usefulness of HRAD work
- 06:21, 27 May 2020 (diff | hist) . . (+17) . . Highly reliable agent designs (current)
- 06:20, 27 May 2020 (diff | hist) . . (+116) . . Highly reliable agent designs
- 06:19, 27 May 2020 (diff | hist) . . (+318) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 06:14, 27 May 2020 (diff | hist) . . (+108) . . Goalpost for usefulness of HRAD work
- 05:16, 27 May 2020 (diff | hist) . . (+43) . . Something like realism about rationality (→See also)
- 05:16, 27 May 2020 (diff | hist) . . (+62) . . Goalpost for usefulness of HRAD work
- 05:15, 27 May 2020 (diff | hist) . . (0) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 05:15, 27 May 2020 (diff | hist) . . (0) . . List of disagreements in AI safety (→Machine learning safety)
- 05:13, 27 May 2020 (diff | hist) . . (0) . . Competence gap
- 05:13, 27 May 2020 (diff | hist) . . (+26) . . Competence gap
- 05:13, 27 May 2020 (diff | hist) . . (-11) . . Competence gap
- 04:41, 27 May 2020 (diff | hist) . . (+285) . . Competence gap
- 04:38, 27 May 2020 (diff | hist) . . (+190) . . Competence gap
- 04:22, 27 May 2020 (diff | hist) . . (-1,811) . . List of disagreements in AI safety (→Machine learning safety)
- 04:22, 27 May 2020 (diff | hist) . . (+1,828) . . N Competence gap (Created page with "to what extent paul's approach looks like humans trying to align arbitrarily large black boxes ("corralling hostile superintelligences") vs humans+pretty smart aligned AIs try...")
- 01:07, 27 May 2020 (diff | hist) . . (+464) . . N Corrigibility (Created page with "'''Corrigibility''' is a term used in AI safety with multiple/unclear meanings. I think the term was originally used by MIRI to mean something like an AI that allowed hum...")
- 00:53, 27 May 2020 (diff | hist) . . (-1,316) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 00:53, 27 May 2020 (diff | hist) . . (+1,317) . . Goalpost for usefulness of HRAD work
- 00:48, 27 May 2020 (diff | hist) . . (+209) . . N Highly reliable agent designs (Created page with "'''Highly reliable agent designs''' is the kind of pure-math research related to agency, etc. that is done at MIRI. List of disagreements in AI safety#Highly reliable agent...")
- 00:47, 27 May 2020 (diff | hist) . . (+43) . . N HRAD (Redirected page to Highly reliable agent designs) (current) (Tag: New redirect)
- 00:47, 27 May 2020 (diff | hist) . . (+472) . . N Goalpost for usefulness of HRAD work (Created page with "There's a pattern I see where: * people advocating HRAD research bring up historical cases like Turing, Shannon, etc. where formalization worked well * people arguing aga...")
- 00:45, 27 May 2020 (diff | hist) . . (+43) . . List of disagreements in AI safety (→Highly reliable agent designs)
- 00:38, 27 May 2020 (diff | hist) . . (+97) . . Resource overhang
- 05:55, 26 May 2020 (diff | hist) . . (+61) . . N Hardware overhang (Created page with "==See also== * Resource overhang Category:AI safety")
- 04:23, 26 May 2020 (diff | hist) . . (0) . . People watching (→Insights/red pills)
- 04:03, 26 May 2020 (diff | hist) . . (+125) . . People watching (→Insights/red pills)
- 03:00, 26 May 2020 (diff | hist) . . (+691) . . AI prepping
- 02:45, 26 May 2020 (diff | hist) . . (-400) . . List of disagreements in AI safety (→Takeoff dynamics)
- 02:45, 26 May 2020 (diff | hist) . . (+461) . . N Resource overhang (Created page with " ==Resource overhang and AI takeoff== Whether we are already in hardware overhang / other "resource bonanza". So whether we are in overhang depends on whether future earl...")
- 02:44, 26 May 2020 (diff | hist) . . (+23) . . List of disagreements in AI safety (→Takeoff dynamics)
- 01:25, 26 May 2020 (diff | hist) . . (+88) . . Secret sauce for intelligence
- 00:05, 26 May 2020 (diff | hist) . . (+777) . . Secret sauce for intelligence (→Evidence)
- 23:46, 25 May 2020 (diff | hist) . . (+259) . . Lumpiness
- 01:37, 25 May 2020 (diff | hist) . . (+255) . . Architecture
- 23:17, 23 May 2020 (diff | hist) . . (-2) . . List of teams at OpenAI
- 23:17, 23 May 2020 (diff | hist) . . (-34) . . List of teams at OpenAI
- 23:16, 23 May 2020 (diff | hist) . . (+25) . . List of teams at OpenAI
- 23:16, 23 May 2020 (diff | hist) . . (+44) . . List of teams at OpenAI
- 23:16, 23 May 2020 (diff | hist) . . (+87) . . List of teams at OpenAI
- 20:25, 23 May 2020 (diff | hist) . . (+43) . . N Quick review (Redirected page to Bury cards to speed up review) (current) (Tag: New redirect)
- 04:23, 23 May 2020 (diff | hist) . . (+59) . . Spaced proof review routine
- 23:47, 22 May 2020 (diff | hist) . . (-356) . . Spaced proof review routine
- 23:46, 22 May 2020 (diff | hist) . . (+455) . . Choosing problems for spaced proof review (current)
- 23:44, 22 May 2020 (diff | hist) . . (0) . . Spaced proof review routine
- 23:43, 22 May 2020 (diff | hist) . . (+189) . . Spaced proof review routine
- 05:08, 22 May 2020 (diff | hist) . . (+638) . . Narrow window argument against continuous takeoff
- 03:51, 22 May 2020 (diff | hist) . . (+63) . . N Soft takeoff keyhole (Redirected page to Narrow window argument against continuous takeoff) (current) (Tag: New redirect)
- 03:50, 22 May 2020 (diff | hist) . . (+105) . . Narrow window argument against continuous takeoff
- 03:50, 22 May 2020 (diff | hist) . . (+63) . . N Continuous takeoff keyhole (Redirected page to Narrow window argument against continuous takeoff) (current) (Tag: New redirect)
- 03:49, 22 May 2020 (diff | hist) . . (+1,246) . . Narrow window argument against continuous takeoff
- 03:44, 22 May 2020 (diff | hist) . . (+1,031) . . N Narrow window argument against continuous takeoff (Created page with " "When you fold a whole chain of differential equations in on itself like this, it should either peter out rapidly as improvements fail to yield further improvements, or else...")
- 03:38, 22 May 2020 (diff | hist) . . (+56) . . List of disagreements in AI safety (→Takeoff dynamics)
- 03:37, 22 May 2020 (diff | hist) . . (+237) . . Spaced repetition allows graceful deprecation of experiments
- 03:32, 22 May 2020 (diff | hist) . . (0) . . Spaced repetition allows graceful deprecation of experiments
- 03:32, 22 May 2020 (diff | hist) . . (+322) . . Spaced repetition allows graceful deprecation of experiments
- 03:29, 22 May 2020 (diff | hist) . . (+92) . . Spaced repetition as soft alarm clock
- 03:27, 22 May 2020 (diff | hist) . . (+116) . . N Anki deck options (Created page with "* Deck options for proof cards * Incremental reading in Anki#My deck options Category:Spaced repetition")
- 03:26, 22 May 2020 (diff | hist) . . (+606) . . Spaced repetition allows graceful deprecation of experiments
- 01:43, 22 May 2020 (diff | hist) . . (+139) . . Spaced repetition allows graceful deprecation of experiments
- 01:38, 22 May 2020 (diff | hist) . . (-1,831) . . Spaced repetition experiments take months to complete (Redirected page to Iteration cadence for spaced repetition experiments) (current) (Tag: New redirect)
- 01:38, 22 May 2020 (diff | hist) . . (+1,808) . . Iteration cadence for spaced repetition experiments
- 01:37, 22 May 2020 (diff | hist) . . (+67) . . List of experiments with Anki (→See also)
- 01:36, 22 May 2020 (diff | hist) . . (+58) . . Spaced repetition experiments take months to complete (→See also)
- 01:35, 22 May 2020 (diff | hist) . . (+82) . . Spaced repetition experiments take months to complete
- 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...")
- 21:27, 18 May 2020 (diff | hist) . . (+9) . . Timeline of my involvement in AI safety (current)
- 21:24, 18 May 2020 (diff | hist) . . (+14) . . Timeline of my involvement in AI safety
- 21:24, 18 May 2020 (diff | hist) . . (+164) . . Timeline of my involvement in AI safety
- 21:21, 18 May 2020 (diff | hist) . . (+12) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 21:21, 18 May 2020 (diff | hist) . . (+46) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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")
- 21:16, 18 May 2020 (diff | hist) . . (+92) . . AI safety technical pipeline does not teach how to start having novel thoughts
- 21:15, 18 May 2020 (diff | hist) . . (+317) . . AI safety technical pipeline does not teach how to start having novel thoughts
- 21:13, 18 May 2020 (diff | hist) . . (+57) . . AI safety lacks a space to ask stupid or ballsy questions
- 21:11, 18 May 2020 (diff | hist) . . (+256) . . AI safety lacks a space to ask stupid or ballsy questions
- 21:10, 18 May 2020 (diff | hist) . . (+64) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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) . . (+56) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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...")
- 20:45, 18 May 2020 (diff | hist) . . (+554) . . AI safety is not a community
- 20:39, 18 May 2020 (diff | hist) . . (+53) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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) . . (+35) . . My current thoughts on the technical AI safety pipeline (outside academia)
- 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...")
- 20:26, 18 May 2020 (diff | hist) . . (+479) . . AI safety technical pipeline does not teach how to start having novel thoughts
(newest | oldest) View (newer 250 | older 250) (20 | 50 | 100 | 250 | 500)