LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

Wireheading is in the eye of the beholder
Stuart_Armstrong · 2019-01-30T18:23:07.143Z · comments (10)
Masculine Virtues
Jacob Falkovich (Jacobian) · 2019-01-30T16:03:56.000Z · comments (32)
Deconfusing Logical Counterfactuals
Chris_Leong · 2019-01-30T15:13:41.436Z · comments (16)
Book Trilogy Review: Remembrance of Earth’s Past (The Three Body Problem)
Zvi · 2019-01-30T01:10:00.414Z · comments (16)
Alignment Newsletter #43
rohinmshah · 2019-01-29T21:10:02.373Z · comments (2)
The Question Of Perception
The Arkon · 2019-01-29T20:59:23.450Z · comments (18)
[question] Which textbook would you recommend to learn decision theory?
supermartingale · 2019-01-29T20:48:11.577Z · answers+comments (6)
Towards equilibria-breaking methods
ryan_b · 2019-01-29T16:19:57.564Z · comments (3)
Can there be an indescribable hellworld?
Stuart_Armstrong · 2019-01-29T15:00:54.481Z · comments (19)
How much can value learning be disentangled?
Stuart_Armstrong · 2019-01-29T14:17:00.601Z · comments (30)
Techniques for optimizing worst-case performance
paulfchristiano · 2019-01-28T21:29:53.164Z · comments (12)
[Link] Did AlphaStar just click faster?
Aidan O'Gara · 2019-01-28T20:23:08.196Z · comments (14)
"Giftedness" and Genius, Crucial Differences
ArthurLidia · 2019-01-28T20:22:37.664Z · comments (None)
Quantum Neural Net and You
ScrubbyBubbles · 2019-01-28T18:42:01.456Z · comments (4)
A small example of one-step hypotheticals
Stuart_Armstrong · 2019-01-28T16:12:02.722Z · comments (None)
[question] How would one go about defining the ideal personality compatibility test?
digitalcaffeine · 2019-01-28T03:02:04.777Z · answers+comments (4)
[link] Solomonoff induction and belief in God
Berkeley Beetle · 2019-01-28T03:01:04.584Z · comments (3)
Practical Considerations Regarding Political Polarization
joshuabecker · 2019-01-27T22:26:15.048Z · comments (None)
"The Unbiased Map"
JohnBuridan · 2019-01-27T19:08:10.051Z · comments (1)
Prediction Contest 2018: Scores and Retrospective
jbeshir · 2019-01-27T17:20:15.245Z · comments (5)
Freely Complying With the Ideal: A Theory of Happiness
Solnassant · 2019-01-27T12:28:59.810Z · comments (2)
Confessions of an Abstraction Hater
Martin Sustrik (sustrik) · 2019-01-27T05:50:01.066Z · comments (4)
Río Grande: judgment calls
KatjaGrace · 2019-01-27T03:50:01.102Z · comments (5)
[link] "Forecasting Transformative AI: An Expert Survey", Gruetzemacher et al 2019
gwern · 2019-01-27T02:34:57.214Z · comments (None)
Building up to an Internal Family Systems model
Kaj_Sotala · 2019-01-26T12:25:11.162Z · comments (84)
Future directions for narrow value learning
rohinmshah · 2019-01-26T02:36:51.532Z · comments (4)
[question] For what do we need Superintelligent AI?
avturchin · 2019-01-25T15:01:01.772Z · answers+comments (18)
[link] "AlphaStar: Mastering the Real-Time Strategy Game StarCraft II", DeepMind [won 10 of 11 games against human pros]
gwern · 2019-01-24T20:49:01.350Z · comments (52)
Thoughts on reward engineering
paulfchristiano · 2019-01-24T20:15:05.251Z · comments (30)
From Personal to Prison Gangs: Enforcing Prosocial Behavior
johnswentworth · 2019-01-24T18:07:33.262Z · comments (24)
[question] Is Agent Simulates Predictor a "fair" problem?
Chris_Leong · 2019-01-24T13:18:13.745Z · answers+comments (19)
[question] In what way has the generation after us "gone too far"?
Elo · 2019-01-24T10:22:34.063Z · answers+comments (3)
The human side of interaction
rohinmshah · 2019-01-24T10:14:33.906Z · comments (5)
South Bay Meetup
David Friedman (david-friedman) · 2019-01-24T05:29:20.454Z · comments (None)
Allowing a formal proof system to self improve while avoiding Lobian obstacles.
Donald Hobson (donald-hobson) · 2019-01-23T23:04:43.524Z · comments (4)
Rationality Café No. 9 - The Sequences, Part 1; Section C b
thegreatnick · 2019-01-23T22:41:10.193Z · comments (None)
Starting to see 2 months later
Pausecafe · 2019-01-23T20:46:45.901Z · comments (3)
Edinburgh SSC meetup ϛ
Hamish Peter Todd (hamish-peter-todd) · 2019-01-23T18:36:17.108Z · comments (None)
S-Curves for Trend Forecasting
Matt Goldenberg (mr-hire) · 2019-01-23T18:17:56.436Z · comments (22)
One-step hypothetical preferences
Stuart_Armstrong · 2019-01-23T15:14:52.063Z · comments (6)
Shanghai LessWrong Meetup
Mindey · 2019-01-23T12:59:28.613Z · comments (10)
Games in Kocherga club: Fallacymania, Tower of Chaos, Scientific Discovery
Alexander230 · 2019-01-23T11:57:49.020Z · comments (None)
Could declining interest to the Doomsday Argument explain the Doomsday Argument?
avturchin · 2019-01-23T11:51:57.012Z · comments (3)
Link: That Time a Guy Tried to Build a Utopia for Mice and it all Went to Hell
Alexei · 2019-01-23T06:27:05.219Z · comments (6)
Learning with catastrophes
paulfchristiano · 2019-01-23T03:01:26.397Z · comments (9)
The Relationship Between Hierarchy and Wealth
sarahconstantin · 2019-01-23T02:00:00.467Z · comments (8)
Too Smart for My Own Good
isovector · 2019-01-22T17:51:10.960Z · comments (4)
[meta] Vote counting bug?
Richard_Ngo (ricraz) · 2019-01-22T15:44:48.154Z · comments (8)
Stale air / high CO2 may decrease your cognitive function
Yoav Ravid · 2019-01-22T12:52:06.070Z · comments (6)
[link] Why don't people use formal methods?
John_Maxwell (John_Maxwell_IV) · 2019-01-22T09:39:46.721Z · comments (5)
next page (older posts) →