LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

[link] October gwern.net links
gwern · 2018-11-01T01:11:28.763Z · comments (8)
Goodhart's Law and Genies
thomascolthurst · 2018-11-01T01:38:41.933Z · comments (5)
Linkpost: Arena’s New Opening Hand Rule Has Huge Implications For How We Play the Game
Zvi · 2018-11-01T12:30:00.810Z · comments (1)
[link] Implementations of immortality
Richard_Ngo (ricraz) · 2018-11-01T14:20:01.494Z · comments (11)
What is ambitious value learning?
Rohin Shah (rohinmshah) · 2018-11-01T16:20:27.865Z · comments (28)
Discussion on the machine learning approach to AI safety
Vika · 2018-11-01T20:54:39.195Z · comments (3)
Meta-execution
paulfchristiano · 2018-11-01T22:18:10.656Z · comments (1)
Kansas City SSC Readers Meetup
Todd326 · 2018-11-02T10:45:17.405Z · comments (0)
Embedded World-Models
abramdemski · 2018-11-02T16:07:20.946Z · comments (16)
My Intuitions on Counterlogical Reasoning
DragonGod · 2018-11-02T21:36:15.494Z · comments (0)
The easy goal inference problem is still hard
paulfchristiano · 2018-11-03T14:41:55.464Z · comments (20)
[meta] New GreaterWrong feature: image zoom + image slideshows
Said Achmiz (SaidAchmiz) · 2018-11-04T07:34:44.907Z · comments (3)
Robust Delegation
abramdemski · 2018-11-04T16:38:38.750Z · comments (10)
No Really, Why Aren't Rationalists Winning?
Sailor Vulcan · 2018-11-04T18:11:15.586Z · comments (90)
Beliefs at different timescales
Nisan · 2018-11-04T20:10:59.223Z · comments (12)
When does rationality-as-search have nontrivial implications?
nostalgebraist · 2018-11-04T22:42:01.452Z · comments (11)
Humans can be assigned any values whatsoever…
Stuart_Armstrong · 2018-11-05T14:26:41.337Z · comments (27)
Boulder Slate Star Codex Meetup
corticalcircuitry · 2018-11-05T15:01:00.180Z · comments (0)
[link] Speculations on improving debating
Richard_Ngo (ricraz) · 2018-11-05T16:10:02.799Z · comments (4)
Octopath Traveler: Spoiler-Free Review
Zvi · 2018-11-05T17:50:00.986Z · comments (1)
Alignment Newsletter #31
Rohin Shah (rohinmshah) · 2018-11-05T23:50:02.432Z · comments (0)
Subsystem Alignment
abramdemski · 2018-11-06T16:16:45.656Z · comments (12)
[link] The Vulnerable World Hypothesis (by Bostrom)
Ben Pace (Benito) · 2018-11-06T20:05:27.496Z · comments (17)
Triangle SSC Meetup
willbobaggins · 2018-11-06T22:43:09.390Z · comments (0)
Rationality of demonstrating & voting
bfinn · 2018-11-07T00:09:44.239Z · comments (21)
Reframing a Crush: Distilling the "like" out of "like like"
squidious · 2018-11-07T02:50:01.171Z · comments (0)
Paris SSC Meetup
fbreton · 2018-11-07T10:04:43.575Z · comments (0)
Latent Variables and Model Mis-Specification
jsteinhardt · 2018-11-07T14:48:40.434Z · comments (8)
Bayes Questions
Bucky · 2018-11-07T16:54:38.800Z · comments (13)
[link] Burnout: What it is and how to Treat it.
Elizabeth (pktechgirl) · 2018-11-07T22:02:23.649Z · comments (0)
What are Universal Inductors, Again?
Diffractor · 2018-11-07T22:32:57.364Z · comments (0)
[meta] The new Effective Altruism forum just launched
habryka (habryka4) · 2018-11-08T01:59:01.502Z · comments (6)
[link] Is Copenhagen or Many Worlds true? An experiment. What? Yes.
Jonathanm · 2018-11-08T10:10:20.396Z · comments (3)
[link] On first looking into Russell's History
Richard_Ngo (ricraz) · 2018-11-08T11:20:00.935Z · comments (6)
Embedded Curiosities
Scott Garrabrant · 2018-11-08T14:19:32.546Z · comments (1)
Help Me Refactor Myself I am Lost
Pausecafe · 2018-11-08T20:18:14.150Z · comments (20)
Multi-Agent Overoptimization, and Embedded Agent World Models
Davidmanheim · 2018-11-08T20:33:00.499Z · comments (3)
Update the best textbooks on every subject list
ryan_b · 2018-11-08T20:54:35.300Z · comments (14)
Prediction-Augmented Evaluation Systems
ozziegooen · 2018-11-09T10:55:36.181Z · comments (12)
[link] Open AI: Can we rule out near-term AGI?
ShardPhoenix · 2018-11-09T12:16:18.821Z · comments (1)
Model Mis-specification and Inverse Reinforcement Learning
Owain_Evans · 2018-11-09T15:33:02.630Z · comments (3)
Current AI Safety Roles for Software Engineers
ozziegooen · 2018-11-09T20:57:16.159Z · comments (9)
Real-time hiring with prediction markets
ryan_b · 2018-11-09T22:10:18.576Z · comments (9)
[link] Specification gaming examples in AI
Samuel Rødal (samuel-rodal) · 2018-11-10T12:00:29.369Z · comments (6)
Preface to the sequence on iterated amplification
paulfchristiano · 2018-11-10T13:24:13.200Z · comments (8)
Productivity: Instrumental Rationality
frdk666 · 2018-11-10T14:58:36.336Z · comments (7)
Competitive Markets as Distributed Backprop
johnswentworth · 2018-11-10T16:47:37.622Z · comments (10)
Reconciling Left and Right, from the Bottom-Up
jesseduffield · 2018-11-11T08:36:05.554Z · comments (2)
Future directions for ambitious value learning
Rohin Shah (rohinmshah) · 2018-11-11T15:53:52.888Z · comments (9)
“She Wanted It”
sarahconstantin · 2018-11-11T22:00:01.645Z · comments (19)
next page (older posts) →