LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

[link] High-precision claims may be refuted without being replaced with other high-precision claims
jessicata (jessica.liu.taylor) · 2020-01-30T23:08:33.792Z · comments (30)
[question] how has this forum changed your life?
Jon Ronson (jonronson-mac-com) · 2020-01-30T21:54:56.037Z · answers+comments (20)
[link] Artificial Intelligence, Values and Alignment
Gordon Seidoh Worley (gworley) · 2020-01-30T19:48:59.002Z · comments (1)
If brains are computers, what kind of computers are they? (Dennett transcript)
Ben Pace (Benito) · 2020-01-30T05:07:00.345Z · comments (9)
Value uncertainty
MichaelA · 2020-01-29T20:16:18.758Z · comments (3)
Towards deconfusing values
Gordon Seidoh Worley (gworley) · 2020-01-29T19:28:08.200Z · comments (4)
[AN #84] Reviewing AI alignment work in 2018-19
Rohin Shah (rohinmshah) · 2020-01-29T18:30:01.738Z · comments (0)
[link] Slide deck: Introduction to AI Safety
Aryeh Englander (alenglander) · 2020-01-29T15:57:04.979Z · comments (0)
The Skewed and the Screwed: When Mating Meets Politics
Jacob Falkovich (Jacobian) · 2020-01-29T15:50:31.681Z · comments (6)
Twin Cities Meetup 2/1/20: Estimation, Collective Wisdom, and Survey Data
Drake Thomas (RavenclawPrefect) · 2020-01-29T14:55:31.791Z · comments (0)
TAISU - Technical AI Safety Unconference
Linda Linsefors · 2020-01-29T13:31:36.431Z · comments (4)
[meta] Mod Notice about Election Discussion
Vaniver · 2020-01-29T01:35:53.947Z · comments (16)
Survival and Flourishing grant applications open until March 7th ($0.8MM-$1.5MM planned for dispersal)
habryka (habryka4) · 2020-01-28T23:36:40.191Z · comments (0)
Potential Ways to Fight Mazes
Zvi · 2020-01-28T22:50:00.352Z · comments (9)
[link] Draining the swamp
jasoncrawford · 2020-01-28T21:37:03.542Z · comments (0)
[question] Hello, is it you I'm looking for?
Knuckels McGinty · 2020-01-28T20:56:09.191Z · answers+comments (15)
Using vector fields to visualise preferences and make them consistent
MichaelA · 2020-01-28T19:44:43.042Z · comments (32)
[link] If Van der Waals was a neural network
George3d6 · 2020-01-28T18:38:31.561Z · comments (3)
Assortative Mating And Autism
Scott Alexander (Yvain) · 2020-01-28T18:20:02.223Z · comments (2)
[question] Algorithms vs Compute
johnswentworth · 2020-01-28T17:34:31.795Z · answers+comments (11)
Appendix: how a subagent could get powerful
Stuart_Armstrong · 2020-01-28T15:28:56.434Z · comments (14)
Rationalist prepper thread
avturchin · 2020-01-28T13:42:05.628Z · comments (15)
Cambridge LW/SSC Meetup: Prediction Training
NoSignalNoNoise (AspiringRationalist) · 2020-01-28T05:25:07.466Z · comments (0)
An Empistemically Rational Superbowl
NoSignalNoNoise (AspiringRationalist) · 2020-01-28T04:05:40.095Z · comments (1)
AI Alignment 2018-19 Review
Rohin Shah (rohinmshah) · 2020-01-28T02:19:52.782Z · comments (6)
Review: How to Read a Book (Mortimer Adler, Charles Van Doren)
Elizabeth (pktechgirl) · 2020-01-27T21:10:01.266Z · comments (8)
[question] What research has been done on the altruistic impact of the usual good actions?
Alexei · 2020-01-27T19:33:16.818Z · answers+comments (6)
Healing vs. exercise analogies for emotional work
Kaj_Sotala · 2020-01-27T19:10:01.477Z · comments (8)
[link] The Bentham Prize at Metaculus
AABoyles · 2020-01-27T14:27:21.172Z · comments (4)
Porting My Rhythm Setup
jefftk (jkaufman) · 2020-01-26T21:20:02.070Z · comments (0)
UML VIII: Linear Predictors (2)
Rafael Harth (sil-ver) · 2020-01-26T20:09:28.305Z · comments (2)
[question] What happens if we reverse Newcomb's Paradox and replace it with two negative sums? Doesn't it kinda maybe affirm Roko's Basilisk?
Habby · 2020-01-26T18:08:40.966Z · answers+comments (3)
[link] On hiding the source of knowledge
jessicata (jessica.liu.taylor) · 2020-01-26T02:48:51.310Z · comments (40)
Hedonic asymmetries
paulfchristiano · 2020-01-26T02:10:01.323Z · comments (22)
Moral public goods
paulfchristiano · 2020-01-26T00:10:01.803Z · comments (74)
Coordination as a Scarce Resource
johnswentworth · 2020-01-25T23:32:36.309Z · comments (22)
[question] Are the bad epistemic conditions global?
jmh · 2020-01-25T23:31:21.283Z · answers+comments (1)
Material Goods as an Abundant Resource
johnswentworth · 2020-01-25T23:23:14.489Z · comments (9)
Constraints & Slackness as a Worldview Generator
johnswentworth · 2020-01-25T23:18:54.562Z · comments (4)
Technology Changes Constraints
johnswentworth · 2020-01-25T23:13:17.428Z · comments (6)
SSC Zürich February Meetup
Vitor · 2020-01-25T17:21:46.229Z · comments (0)
Ten Causes of Mazedom
Zvi · 2020-01-25T13:40:00.434Z · comments (6)
[link] On the ontological development of consciousness
jessicata (jessica.liu.taylor) · 2020-01-25T05:56:43.244Z · comments (7)
[question] Have epistemic conditions always been this bad?
Wei Dai (Wei_Dai) · 2020-01-25T04:42:52.190Z · answers+comments (106)
Cambridge Prediction Game
NoSignalNoNoise (AspiringRationalist) · 2020-01-25T03:57:59.721Z · comments (3)
SSC Halifax Meetup -- January 25
interstice · 2020-01-25T01:15:13.090Z · comments (0)
Litany Against Anger
namespace (ingres) · 2020-01-25T00:56:53.958Z · comments (2)
AI alignment concepts: philosophical breakers, stoppers, and distorters
JustinShovelain · 2020-01-24T19:23:10.902Z · comments (3)
The two-layer model of human values, and problems with synthesizing preferences
Kaj_Sotala · 2020-01-24T15:17:33.638Z · comments (16)
[question] How much do we know about how brains learn?
Kenny · 2020-01-24T14:46:47.185Z · answers+comments (0)
next page (older posts) →