LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

How safe "safe" AI development?
G Gordon Worley III (gworley) · 2018-02-28T23:21:50.307Z · score: 27 (10 votes) · comments (1)
Beyond algorithmic equivalence: self-modelling
Stuart_Armstrong · 2018-02-28T16:55:55.161Z · score: 29 (6 votes) · comments (4)
Beyond algorithmic equivalence: algorithmic noise
Stuart_Armstrong · 2018-02-28T16:55:36.036Z · score: 29 (8 votes) · comments (4)
Using the universal prior for logical uncertainty (retracted)
cousin_it · 2018-02-28T13:07:23.644Z · score: 39 (10 votes) · comments (13)
[meta] 2/27/08 Update – Frontpage 3.0
Raemon · 2018-02-28T06:26:23.255Z · score: 46 (10 votes) · comments (21)
TDT for Humans
alkjash · 2018-02-28T05:40:00.450Z · score: 60 (16 votes) · comments (5)
Set Up for Success: Insights from 'Naïve Set Theory'
TurnTrout · 2018-02-28T02:01:43.790Z · score: 62 (18 votes) · comments (40)
Intuition should be applied at the lowest possible level
sil ver (sil-ver) · 2018-02-27T22:58:42.000Z · score: 29 (10 votes) · comments (9)
The sad state of Rationality Zürich - Effective Altruism Zürich included
roland · 2018-02-27T14:51:05.881Z · score: -13 (25 votes) · comments (47)
The worst trolley problem in the world
CronoDAS · 2018-02-27T03:56:26.159Z · score: -1 (4 votes) · comments (1)
Categories of Sacredness
Zvi · 2018-02-27T02:00:00.403Z · score: 55 (16 votes) · comments (36)
More on the Linear Utility Hypothesis and the Leverage Prior
AlexMennen · 2018-02-26T23:53:35.605Z · score: 37 (9 votes) · comments (4)
Goal Factoring
alkjash · 2018-02-26T23:30:01.074Z · score: 24 (5 votes) · comments (2)
Inconvenience Is Qualitatively Bad
Alicorn · 2018-02-26T23:27:05.474Z · score: 157 (51 votes) · comments (50)
The Hamming Problem of Group Rationality
PDV · 2018-02-26T18:59:33.745Z · score: 9 (18 votes) · comments (37)
Focusing
alkjash · 2018-02-26T06:10:00.614Z · score: 42 (14 votes) · comments (17)
Mapping the Archipelago
alkjash · 2018-02-26T05:09:49.833Z · score: 45 (14 votes) · comments (25)
[meta] Experimental Open Threads
Chris_Leong · 2018-02-26T03:13:16.999Z · score: 66 (15 votes) · comments (5)
Walkthrough of 'Formalizing Convergent Instrumental Goals'
TurnTrout · 2018-02-26T02:20:09.294Z · score: 27 (6 votes) · comments (2)
Will AI See Sudden Progress?
KatjaGrace · 2018-02-26T00:41:14.514Z · score: 55 (15 votes) · comments (8)
Self-regulation of safety in AI research
G Gordon Worley III (gworley) · 2018-02-25T23:17:44.720Z · score: 33 (10 votes) · comments (6)
The abruptness of nuclear weapons
paulfchristiano · 2018-02-25T17:40:35.656Z · score: 95 (35 votes) · comments (51)
[link] Likelihood of discontinuous progress around the development of AGI
vedevazz · 2018-02-25T15:13:28.177Z · score: 10 (5 votes) · comments (2)
Open-Source Monasticism
Nathan Rosquist (nathan-rosquist) · 2018-02-25T13:52:01.182Z · score: 69 (20 votes) · comments (7)
Passing Troll Bridge
Diffractor · 2018-02-25T08:21:17.000Z · score: 1 (1 votes) · comments (0)
Three Miniatures
alkjash · 2018-02-25T05:40:00.911Z · score: 41 (11 votes) · comments (8)
[link] Arguments about fast takeoff
paulfchristiano · 2018-02-25T04:53:36.083Z · score: 101 (33 votes) · comments (54)
[meta] Meta-tations on Moderation: Towards Public Archipelago
Raemon · 2018-02-25T03:59:32.243Z · score: 173 (56 votes) · comments (173)
Lessons from the Cold War on Information Hazards: Why Internal Communication is Critical
Gentzel · 2018-02-24T23:34:33.250Z · score: 61 (16 votes) · comments (6)
What we talk about when we talk about maximising utility
ricraz · 2018-02-24T22:33:28.390Z · score: 27 (8 votes) · comments (18)
[meta] Links with underscores
ShardPhoenix · 2018-02-24T11:32:48.752Z · score: 2 (1 votes) · comments (3)
A useful level distinction
Charlie Steiner · 2018-02-24T06:39:47.558Z · score: 26 (6 votes) · comments (4)
CoZE 2
alkjash · 2018-02-24T05:40:00.805Z · score: 35 (9 votes) · comments (2)
On Building Theories of History
Samo Burja · 2018-02-23T23:40:55.722Z · score: 69 (17 votes) · comments (20)
Mythic Mode
Valentine · 2018-02-23T22:45:06.709Z · score: 101 (47 votes) · comments (75)
[link] The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation
G Gordon Worley III (gworley) · 2018-02-23T21:42:20.604Z · score: 15 (4 votes) · comments (8)
Two types of mathematician
drossbucket · 2018-02-23T19:26:19.551Z · score: 112 (35 votes) · comments (38)
June 2012: 0/33 Turing Award winners predict computers beating humans at go within next 10 years.
betterthanwell · 2018-02-23T11:25:12.092Z · score: 49 (15 votes) · comments (14)
Design 2
alkjash · 2018-02-23T06:20:00.656Z · score: 38 (12 votes) · comments (12)
[link] AI Alignment and Phenomenal Consciousness
G Gordon Worley III (gworley) · 2018-02-23T01:21:36.808Z · score: 10 (2 votes) · comments (0)
Explanation vs Rationalization
abramdemski · 2018-02-22T23:46:48.377Z · score: 31 (8 votes) · comments (10)
The map has gears. They don't always turn.
abramdemski · 2018-02-22T20:16:13.095Z · score: 54 (14 votes) · comments (0)
The Intelligent Social Web
Valentine · 2018-02-22T18:55:36.414Z · score: 163 (66 votes) · comments (87)
The Three Stages Of Model Development
katerinjo · 2018-02-22T14:33:19.081Z · score: 52 (13 votes) · comments (7)
Pain, fear, sex, and higher order preferences
Stuart_Armstrong · 2018-02-22T11:30:41.123Z · score: 11 (6 votes) · comments (3)
TAPs 2
alkjash · 2018-02-22T05:10:00.490Z · score: 43 (12 votes) · comments (2)
Robustness to Scale
Scott Garrabrant · 2018-02-21T22:55:19.155Z · score: 165 (45 votes) · comments (15)
Don't Condition on no Catastrophes
Scott Garrabrant · 2018-02-21T21:50:31.077Z · score: 82 (26 votes) · comments (8)
[link] The Logic of Science: 2.2
mpr · 2018-02-21T17:28:52.537Z · score: 24 (7 votes) · comments (2)
Yoda Timers 2
alkjash · 2018-02-21T07:40:00.792Z · score: 50 (18 votes) · comments (13)
next page (older posts) →