User contributions
(newest | oldest) View (newer 50 | older 50) (20 | 50 | 100 | 250 | 500)
- 08:23, 20 February 2020 (diff | hist) . . (+1,122) . . My understanding of how IDA works
- 08:21, 20 February 2020 (diff | hist) . . (+2,740) . . N My understanding of how IDA works (Created page with "==explanation== '''Stage 0''': In the beginning, Hugh directly rates actions to provide the initial training data on what Hugh approves of. This is used to train <math>A_0</m...")
- 08:00, 20 February 2020 (diff | hist) . . (+189) . . Future planning
- 07:57, 20 February 2020 (diff | hist) . . (+46) . . Future planning
- 07:56, 20 February 2020 (diff | hist) . . (+578) . . Future planning
- 03:54, 20 February 2020 (diff | hist) . . (+212) . . How doomed are ML safety approaches?
- 03:48, 20 February 2020 (diff | hist) . . (+55) . . N Simple core algorithm for agency (Redirected page to Simple core of consequentialist reasoning) (current) (Tag: New redirect)
- 03:47, 20 February 2020 (diff | hist) . . (+267) . . Future planning
- 03:44, 20 February 2020 (diff | hist) . . (+151) . . How doomed are ML safety approaches?
- 03:32, 20 February 2020 (diff | hist) . . (+135) . . How doomed are ML safety approaches?
- 02:11, 20 February 2020 (diff | hist) . . (+141) . . How doomed are ML safety approaches?
- 02:01, 20 February 2020 (diff | hist) . . (+45) . . How doomed are ML safety approaches?
- 01:58, 20 February 2020 (diff | hist) . . (+173) . . How doomed are ML safety approaches?
- 01:43, 20 February 2020 (diff | hist) . . (+120) . . How doomed are ML safety approaches?
- 01:16, 20 February 2020 (diff | hist) . . (+1) . . How doomed are ML safety approaches?
- 01:14, 20 February 2020 (diff | hist) . . (+186) . . How doomed are ML safety approaches?
- 01:05, 20 February 2020 (diff | hist) . . (+381) . . How doomed are ML safety approaches?
- 01:03, 20 February 2020 (diff | hist) . . (+1) . . How doomed are ML safety approaches?
- 01:03, 20 February 2020 (diff | hist) . . (+120) . . How doomed are ML safety approaches?
- 01:02, 20 February 2020 (diff | hist) . . (+331) . . How doomed are ML safety approaches?
- 01:00, 20 February 2020 (diff | hist) . . (+352) . . How doomed are ML safety approaches?
- 00:59, 20 February 2020 (diff | hist) . . (+240) . . How doomed are ML safety approaches?
- 00:53, 20 February 2020 (diff | hist) . . (+703) . . Soft-hard takeoff
- 00:45, 20 February 2020 (diff | hist) . . (+166) . . How doomed are ML safety approaches?
- 00:44, 20 February 2020 (diff | hist) . . (+401) . . How doomed are ML safety approaches?
- 00:41, 20 February 2020 (diff | hist) . . (+312) . . How doomed are ML safety approaches?
- 00:28, 20 February 2020 (diff | hist) . . (-11) . . How doomed are ML safety approaches?
- 00:27, 20 February 2020 (diff | hist) . . (+29) . . N Paul (Redirected page to Paul Christiano) (current) (Tag: New redirect)
- 00:27, 20 February 2020 (diff | hist) . . (+30) . . N Paul christiano (Created page with "# redirect Paul Christiano")
- 00:26, 20 February 2020 (diff | hist) . . (+1,487) . . N How doomed are ML safety approaches? (Created page with "I want to understand better the MIRI case for thinking that ML-based safety approaches (like paul christiano's agenda) are so hopeless as to not be worth working on (or so...")
- 00:19, 20 February 2020 (diff | hist) . . (+44) . . Future planning
- 23:02, 19 February 2020 (diff | hist) . . (+237) . . Future planning
- 22:36, 19 February 2020 (diff | hist) . . (+183) . . Future planning
- 22:35, 19 February 2020 (diff | hist) . . (+192) . . N Future planning (Created page with "things to talk about: * how doomed ML safety approaches are e.g. see discussion [https://www.greaterwrong.com/posts/suxvE2ddnYMPJN9HD/realism-about-rationality#comment-32dCL2...")
- 05:44, 19 February 2020 (diff | hist) . . (+55) . . Hardware argument for AI timelines
- 03:16, 19 February 2020 (diff | hist) . . (+246) . . N Hardware argument for AI timelines (Created page with "The '''hardware argument''' is a common argument structure for estimating when AGI will be created. see http://www.aleph.se/andart/archives/2010/10/why_early_singularities_ar...")
- 02:55, 19 February 2020 (diff | hist) . . (+55) . . N Simple core algorithm of agency (Redirected page to Simple core of consequentialist reasoning) (current) (Tag: New redirect)
- 02:51, 19 February 2020 (diff | hist) . . (+21) . . N Wei (Redirected page to Wei Dai) (current) (Tag: New redirect)
- 01:01, 19 February 2020 (diff | hist) . . (+1,126) . . Analyzing disagreements
- 00:57, 19 February 2020 (diff | hist) . . (+160) . . N MediaWiki:Common.css (Created page with "→CSS placed here will be applied to all skins: blockquote { border-left: 2px solid #369; padding-left: 10px; margin-right: 15px; margin-left: 0px; }") (current)
- 00:56, 19 February 2020 (diff | hist) . . (+904) . . Analyzing disagreements
- 00:53, 19 February 2020 (diff | hist) . . (+24) . . Main Page
- 00:50, 19 February 2020 (diff | hist) . . (+31) . . N Eliezer (Redirected page to Eliezer Yudkowsky) (current) (Tag: New redirect)
- 00:50, 19 February 2020 (diff | hist) . . (+1,248) . . N Analyzing disagreements (Created page with "a cognitive reduction doesn't ask "why do i have free will?" but instead asks "why do i believe i have free will? what concrete mechanistic facts about the world correspon...")
- 00:33, 19 February 2020 (diff | hist) . . (+196) . . Simple core of consequentialist reasoning
- 00:32, 19 February 2020 (diff | hist) . . (+330) . . Simple core of consequentialist reasoning
- 00:30, 19 February 2020 (diff | hist) . . (+36) . . Simple core of consequentialist reasoning (→See also)
- 00:30, 19 February 2020 (diff | hist) . . (+313) . . Simple core of consequentialist reasoning
- 00:27, 19 February 2020 (diff | hist) . . (+159) . . Simple core of consequentialist reasoning
- 00:26, 19 February 2020 (diff | hist) . . (+48) . . Hardware-driven vs software-driven progress
(newest | oldest) View (newer 50 | older 50) (20 | 50 | 100 | 250 | 500)
