LessWrong 2.0 Reader

View: New · Old · Top

Restrict date range: Today · This week · This month · Last three months · This year · All time

next page (older posts) →

What failure looks like
paulfchristiano · 2019-03-17T20:18:59.800Z · comments (48)
Alignment Research Field Guide
abramdemski · 2019-03-08T19:57:05.658Z · comments (9)
Personalized Medicine For Real
sarahconstantin · 2019-03-04T22:40:00.351Z · comments (16)
Rest Days vs Recovery Days
Unreal · 2019-03-19T22:37:09.194Z · comments (33)
You Have About Five Words
Raemon · 2019-03-12T20:30:18.806Z · comments (71)
The Amish, and Strategic Norms around Technology
Raemon · 2019-03-24T22:16:04.974Z · comments (18)
Subagents, akrasia, and coherence in humans
Kaj_Sotala · 2019-03-25T14:24:18.095Z · comments (31)
[meta] Karma-Change Notifications
jimrandomh · 2019-03-02T02:52:58.291Z · comments (44)
mAIry's room: AI reasoning to solve philosophical problems
Stuart_Armstrong · 2019-03-05T20:24:13.056Z · comments (41)
Subagents, introspective awareness, and blending
Kaj_Sotala · 2019-03-02T12:53:47.282Z · comments (17)
Privacy
Zvi · 2019-03-15T20:20:00.269Z · comments (78)
What I've Learned From My Parents' Arranged Marriage
squidious · 2019-03-26T06:40:00.975Z · comments (16)
The Main Sources of AI Risk?
Daniel Kokotajlo (daniel-kokotajlo) · 2019-03-21T18:28:33.068Z · comments (22)
Dependability
Unreal · 2019-03-26T22:49:37.402Z · comments (39)
Active Curiosity vs Open Curiosity
Unreal · 2019-03-15T16:54:45.389Z · comments (24)
Three ways that "Sufficiently optimized agents appear coherent" can be false
Wei_Dai · 2019-03-05T21:52:35.462Z · comments (3)
Comparison of decision theories (with a focus on logical-counterfactual decision theories)
riceissa · 2019-03-16T21:15:28.768Z · comments (11)
Plans are Recursive & Why This is Important
Ruby · 2019-03-10T01:58:12.649Z · comments (11)
Declarative Mathematics
johnswentworth · 2019-03-21T19:05:08.688Z · comments (10)
[link] In My Culture
Duncan_Sabien · 2019-03-07T07:22:42.982Z · comments (58)
How to Understand and Mitigate Risk
Matt Goldenberg (mr-hire) · 2019-03-12T10:14:19.873Z · comments (30)
Do you like bullet points?
Raemon · 2019-03-26T04:30:59.104Z · comments (38)
[question] Understanding information cascades
jacobjacob · 2019-03-13T10:55:05.932Z · answers+comments (42)
Boeing 737 MAX MCAS as an agent corrigibility failure
shminux · 2019-03-16T01:46:44.455Z · comments (3)
Motivation: You Have to Win in the Moment
Ruby · 2019-03-01T00:26:07.323Z · comments (19)
[question] How much funding and researchers were in AI, and AI Safety, in 2018?
Raemon · 2019-03-03T21:46:59.132Z · answers+comments (11)
Renaming "Frontpage"
Raemon · 2019-03-09T01:23:05.560Z · comments (16)
[link] 'This Waifu Does Not Exist': 100,000 StyleGAN & GPT-2 samples
gwern · 2019-03-01T04:29:16.529Z · comments (6)
Asymptotically Unambitious AGI
michaelcohen (cocoa) · 2019-03-06T01:15:21.621Z · comments (216)
[meta] Please use real names, especially for Alignment Forum?
Wei_Dai · 2019-03-29T02:54:20.812Z · comments (14)
[question] What would you need to be motivated to answer "hard" LW questions?
Raemon · 2019-03-28T20:07:48.747Z · answers+comments (37)
Some thoughts after reading Artificial Intelligence: A Modern Approach
swift_spiral · 2019-03-19T23:39:46.810Z · comments (4)
Parfit's Escape (Filk)
G Gordon Worley III (gworley) · 2019-03-29T02:31:42.981Z · comments (None)
[question] Did the recent blackmail discussion change your beliefs?
Dagon · 2019-03-24T16:06:52.811Z · answers+comments (7)
[question] What's wrong with these analogies for understanding Informed Oversight and IDA?
Wei_Dai · 2019-03-20T09:11:33.613Z · answers+comments (3)
[question] What societies have ever had legal or accepted blackmail?
clone of saturn · 2019-03-17T09:16:55.560Z · answers+comments (23)
How dangerous is it to ride a bicycle without a helmet?
habryka (habryka4) · 2019-03-09T02:58:23.964Z · comments (30)
[question] What are CAIS' boldest near/medium-term predictions?
jacobjacob · 2019-03-28T13:14:32.800Z · answers+comments (17)
Insights from Munkres' Topology
Rafael Harth (sil-ver) · 2019-03-17T16:52:46.256Z · comments (None)
Finding the variables
Stuart_Armstrong · 2019-03-04T19:37:54.696Z · comments (1)
Simplified preferences needed; simplified preferences sufficient
Stuart_Armstrong · 2019-03-05T19:39:55.000Z · comments (6)
[link] Designing agent incentives to avoid side effects
Vika · 2019-03-11T20:55:10.448Z · comments (None)
Alignment Newsletter #48
rohinmshah · 2019-03-11T21:10:02.312Z · comments (14)
Has "politics is the mind-killer" been a mind-killer?
SonnieBailey · 2019-03-17T03:05:06.935Z · comments (26)
Book review: My Hidden Chimp
Bucky · 2019-03-04T09:55:32.362Z · comments (0)
AI Safety Prerequisites Course: Basic abstract representations of computation
RAISE · 2019-03-13T19:38:56.301Z · comments (2)
[question] Willing to share some words that changed your beliefs/behavior?
Duncan_Sabien · 2019-03-23T02:08:37.437Z · answers+comments (4)
A theory of human values
Stuart_Armstrong · 2019-03-13T15:22:44.845Z · comments (13)
A cognitive intervention for wrist pain
rmoehn · 2019-03-17T05:26:58.910Z · comments (24)
[meta] LW Update 2019-01-03 – New All-Posts Page, Author hover-previews and new post-item
habryka (habryka4) · 2019-03-02T04:09:41.029Z · comments (5)
next page (older posts) →