LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

Lisbon SSC Meetup #1
tamkin&popkin · 2019-08-20T12:20:47.424Z · score: 1 (1 votes) · comments (None)
Self-supervised learning & manipulative predictions
steve2152 · 2019-08-20T10:55:51.804Z · score: 4 (1 votes) · comments (None)
Negative "eeny meeny miny moe"
jkaufman · 2019-08-20T02:48:41.509Z · score: 19 (4 votes) · comments (1)
[link] Why I Am Not a Technocrat
Spugpow · 2019-08-20T02:06:16.679Z · score: -2 (2 votes) · comments (None)
A misconception about immigration
limerott · 2019-08-19T22:37:17.875Z · score: 4 (3 votes) · comments (3)
[question] Do We Change Our Minds Less Often Than We Think?
Raemon · 2019-08-19T21:37:08.004Z · score: 21 (3 votes) · comments (1)
Classifying specification problems as variants of Goodhart's Law
Vika · 2019-08-19T20:40:29.499Z · score: 38 (8 votes) · comments (None)
Unstriving
Jacobian · 2019-08-19T14:31:56.786Z · score: 28 (12 votes) · comments (2)
Goodhart's Curse and Limitations on AI Alignment
G Gordon Worley III (gworley) · 2019-08-19T07:57:01.143Z · score: 15 (5 votes) · comments (7)
Raph Koster on Virtual Worlds vs Games (notes)
Raemon · 2019-08-18T19:01:53.768Z · score: 16 (6 votes) · comments (4)
[link] "Can We Survive Technology" by von Neumann
Benito · 2019-08-18T18:58:54.929Z · score: 27 (7 votes) · comments (2)
Prokaryote Multiverse. An argument that potential simulators do not have significantly more complex physics than ours
MakoYass · 2019-08-18T04:22:53.879Z · score: 0 (9 votes) · comments (4)
Neural Nets in Python 1
lifelonglearner · 2019-08-18T02:48:54.903Z · score: 11 (6 votes) · comments (3)
Inspection Paradox as a Driver of Group Separation
shminux · 2019-08-17T21:47:35.812Z · score: 28 (12 votes) · comments (None)
South Bay Meetup
David Friedman (david-friedman) · 2019-08-17T19:56:48.437Z · score: 1 (1 votes) · comments (None)
Problems in AI Alignment that philosophers could potentially contribute to
Wei_Dai · 2019-08-17T17:38:31.757Z · score: 62 (18 votes) · comments (9)
[question] How can you use music to boost learning?
Matthew Barnett (matthew-barnett) · 2019-08-17T06:59:32.582Z · score: 8 (4 votes) · comments (1)
A Primer on Matrix Calculus, Part 3: The Chain Rule
Matthew Barnett (matthew-barnett) · 2019-08-17T01:50:29.439Z · score: 5 (2 votes) · comments (4)
Nashville SSC September Meetup
friedelcraftiness · 2019-08-16T15:16:28.744Z · score: 1 (1 votes) · comments (None)
Beliefs Are For True Things
Davis_Kingsley · 2019-08-15T23:23:33.175Z · score: 8 (9 votes) · comments (5)
[question] What experiments would demonstrate "upper limits of augmented working memory?"
Raemon · 2019-08-15T22:09:14.492Z · score: 29 (11 votes) · comments (2)
Clarifying some key hypotheses in AI alignment
Ben Cottier (ben-cottier) · 2019-08-15T21:29:06.564Z · score: 67 (25 votes) · comments (2)
Tessercube — OpenPGP Made Mobile
Suji Yan (Tedko) · 2019-08-15T09:34:43.355Z · score: 3 (3 votes) · comments (None)
A Primer on Matrix Calculus, Part 2: Jacobians and other fun
Matthew Barnett (matthew-barnett) · 2019-08-15T01:13:16.070Z · score: 17 (7 votes) · comments (6)
Cognitive Benefits of Exercise
adam_scholl · 2019-08-14T21:40:35.145Z · score: 25 (13 votes) · comments (3)
Partial summary of debate with Benquo and Jessicata [pt 1]
Raemon · 2019-08-14T20:02:04.314Z · score: 84 (26 votes) · comments (55)
[link] "Designing agent incentives to avoid reward tampering", DeepMind
gwern · 2019-08-14T16:57:29.228Z · score: 23 (8 votes) · comments (15)
Subagents, trauma and rationality
Kaj_Sotala · 2019-08-14T13:14:46.838Z · score: 51 (25 votes) · comments (2)
Predicted AI alignment event/meeting calendar
rmoehn · 2019-08-14T07:14:57.233Z · score: 22 (8 votes) · comments (6)
Natural laws should be explicit constraints on strategy space
ryan_b · 2019-08-13T20:22:47.933Z · score: 7 (2 votes) · comments (2)
Distance Functions are Hard
Grue_Slinky · 2019-08-13T17:33:15.296Z · score: 40 (26 votes) · comments (13)
Book Review: Secular Cycles
Scott Alexander (Yvain) · 2019-08-13T04:10:01.201Z · score: 53 (27 votes) · comments (3)
A Primer on Matrix Calculus, Part 1: Basic review
Matthew Barnett (matthew-barnett) · 2019-08-12T23:44:37.068Z · score: 19 (7 votes) · comments (1)
[question] What explanatory power does Kahneman's System 2 possess?
ricraz · 2019-08-12T15:23:20.197Z · score: 34 (15 votes) · comments (3)
Mesa-Optimizers and Over-optimization Failure (Optimizing and Goodhart Effects, Clarifying Thoughts - Part 4)
Davidmanheim · 2019-08-12T08:07:01.769Z · score: 11 (7 votes) · comments (3)
Adjectives from the Future: The Dangers of Result-based Descriptions
Pradeep_Kumar · 2019-08-11T19:19:19.139Z · score: 16 (9 votes) · comments (6)
[question] Could we solve this email mess if we all moved to paid emails?
jacobjacob · 2019-08-11T16:31:10.698Z · score: 31 (14 votes) · comments (46)
AI Safety Reading Group
Søren Elverlin (soren-elverlin-1) · 2019-08-11T09:01:20.433Z · score: 16 (8 votes) · comments (6)
[question] Does human choice have to be transitive in order to be rational/consistent?
jmh · 2019-08-11T01:49:23.967Z · score: 9 (6 votes) · comments (6)
Diana Fleischman and Geoffrey Miller - Audience Q&A
Jacobian · 2019-08-10T22:37:53.090Z · score: 37 (19 votes) · comments (14)
Intransitive Preferences You Can't Pump
zulupineapple · 2019-08-09T23:10:36.650Z · score: 2 (3 votes) · comments (2)
Categorial preferences and utility functions
DavidHolmes · 2019-08-09T21:36:22.424Z · score: 9 (6 votes) · comments (5)
[question] What is the state of the ego depletion field?
elityre · 2019-08-09T20:30:44.798Z · score: 25 (9 votes) · comments (6)
Why Gradients Vanish and Explode
Matthew Barnett (matthew-barnett) · 2019-08-09T02:54:44.199Z · score: 27 (14 votes) · comments (9)
AI Forecasting Dictionary (Forecasting infrastructure, part 1)
jacobjacob · 2019-08-08T16:10:51.516Z · score: 37 (17 votes) · comments (None)
[question] Why do humans not have built-in neural i/o channels?
ricraz · 2019-08-08T13:09:54.072Z · score: 25 (11 votes) · comments (24)
Which of these five AI alignment research projects ideas are no good?
rmoehn · 2019-08-08T07:17:28.959Z · score: 25 (9 votes) · comments (13)
Calibrating With Cards
lifelonglearner · 2019-08-08T06:44:44.853Z · score: 21 (10 votes) · comments (None)
[question] Is there a source/market for LW-related t-shirts?
jooyous · 2019-08-08T04:30:17.141Z · score: 7 (3 votes) · comments (3)
Verification and Transparency
DanielFilan · 2019-08-08T01:50:00.935Z · score: 35 (15 votes) · comments (4)
next page (older posts) →