User contributions
(newest | oldest) View (newer 100 | older 100) (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
(newest | oldest) View (newer 100 | older 100) (20 | 50 | 100 | 250 | 500)