LessWrong 2.0 Reader

View: New · Old · Top

← previous page (newer posts) · next page (older posts) →

You are an optimizer. Act like it!
agentydragon · 2020-02-20T23:46:30.240Z · score: 5 (6 votes) · comments (1)
Goal-directed = Model-based RL?
adamShimi · 2020-02-20T19:13:51.342Z · score: 19 (7 votes) · comments (8)
Training Regime Day 6: Seeking Sense
Mark Xu (mark-xu) · 2020-02-20T17:33:29.011Z · score: 7 (4 votes) · comments (5)
Curiosity Killed the Cat and the Asymptotically Optimal Agent
michaelcohen (cocoa) · 2020-02-20T17:28:41.955Z · score: 28 (12 votes) · comments (13)
[question] How do you survive in the humanities?
polymathwannabe · 2020-02-20T15:19:10.598Z · score: 27 (14 votes) · answers+comments (18)
Making Sense of Coronavirus Stats
jmh · 2020-02-20T15:12:51.292Z · score: 21 (8 votes) · comments (25)
Mapping downside risks and information hazards
MichaelA · 2020-02-20T14:46:30.259Z · score: 15 (4 votes) · comments (None)
Tessellating Hills: a toy model for demons in imperfect search
DaemonicSigil · 2020-02-20T00:12:50.125Z · score: 59 (13 votes) · comments (13)
EA Kansas City planning meetup, discussion & open questions
samstowers · 2020-02-19T23:12:21.968Z · score: 7 (4 votes) · comments (None)
On unfixably unsafe AGI architectures
steve2152 · 2020-02-19T21:16:19.544Z · score: 27 (11 votes) · comments (8)
[AN #87]: What might happen as deep learning scales even further?
rohinmshah · 2020-02-19T18:20:01.664Z · score: 29 (10 votes) · comments (None)
Training Regime Day 5: TAPs
Mark Xu (mark-xu) · 2020-02-19T18:11:05.649Z · score: 12 (5 votes) · comments (None)
[question] Does donating to EA make sense in light of the mere addition paradox ?
George (George3d6) · 2020-02-19T14:14:51.569Z · score: 6 (3 votes) · answers+comments (8)
Stuck Exploration
Chris_Leong · 2020-02-19T12:31:55.276Z · score: 16 (6 votes) · comments (6)
[question] Does anyone have a recommended resource about the research on behavioral conditioning, reinforcement, and shaping?
elityre · 2020-02-19T03:58:05.484Z · score: 7 (2 votes) · answers+comments (3)
Assembling Sets for Contra
jkaufman · 2020-02-19T03:40:02.164Z · score: 8 (1 votes) · comments (2)
[question] Is there an intuitive way to explain how much better superforecasters are than regular forecasters?
William_S · 2020-02-19T01:07:52.394Z · score: 15 (7 votes) · answers+comments (5)
We Want MoR (HPMOR Discussion Podcast) Completes Book One
moridinamael · 2020-02-19T00:34:15.864Z · score: 21 (9 votes) · comments (None)
[question] Is there software for goal factoring?
crabman · 2020-02-18T19:55:37.764Z · score: 4 (1 votes) · answers+comments (1)
What are information hazards?
MichaelA · 2020-02-18T19:34:01.706Z · score: 26 (10 votes) · comments (15)
Blog Post Day (Unofficial)
Daniel Kokotajlo (daniel-kokotajlo) · 2020-02-18T19:05:47.140Z · score: 45 (15 votes) · comments (7)
Big Yellow Tractor (Filk)
G Gordon Worley III (gworley) · 2020-02-18T18:43:09.133Z · score: 11 (3 votes) · comments (3)
Training Regime Day 4: Murphyjitsu
Mark Xu (mark-xu) · 2020-02-18T17:33:12.523Z · score: 10 (6 votes) · comments (None)
[question] In a rational world is there a place for ideology?
wachichornia · 2020-02-18T17:09:03.448Z · score: 2 (2 votes) · answers+comments (3)
(In)action rollouts
Stuart_Armstrong · 2020-02-18T14:48:19.160Z · score: 11 (2 votes) · comments (2)
Counterfactuals versus the laws of physics
Stuart_Armstrong · 2020-02-18T13:21:02.232Z · score: 16 (3 votes) · comments (None)
[link] How to actually switch to an artificial body – Gradual remapping
George (George3d6) · 2020-02-18T13:19:07.076Z · score: 9 (5 votes) · comments (2)
Wireheading and discontinuity
Michele Campolo · 2020-02-18T10:49:42.030Z · score: 22 (6 votes) · comments (3)
Set Ups and Summaries
Elizabeth (pktechgirl) · 2020-02-18T05:00:01.056Z · score: 16 (6 votes) · comments (1)
[Productivity] How not to use "Important // Not Urgent"
aaq · 2020-02-17T23:42:31.178Z · score: 24 (9 votes) · comments (None)
Training Regime Day 3: Tips and Tricks
Mark Xu (mark-xu) · 2020-02-17T18:53:24.808Z · score: 19 (9 votes) · comments (3)
Cambridge (UK) SSC meetup
rlms · 2020-02-17T18:41:33.110Z · score: 1 (1 votes) · comments (None)
[link] Jan Bloch's Impossible War
Hivewired · 2020-02-17T16:14:46.033Z · score: 71 (22 votes) · comments (15)
Subagents and impact measures: summary tables
Stuart_Armstrong · 2020-02-17T14:09:32.029Z · score: 11 (2 votes) · comments (2)
Appendix: mathematics of indexical impact measures
Stuart_Armstrong · 2020-02-17T13:22:43.523Z · score: 12 (3 votes) · comments (None)
Stepwise inaction and non-indexical impact measures
Stuart_Armstrong · 2020-02-17T10:32:01.863Z · score: 12 (3 votes) · comments (7)
How to Lurk Less (and benefit others while benefiting yourself)
romeostevensit · 2020-02-17T06:18:54.978Z · score: 66 (29 votes) · comments (11)
Attainable Utility Preservation: Concepts
TurnTrout · 2020-02-17T05:20:09.567Z · score: 30 (8 votes) · comments (13)
[link] On the falsifiability of hypercomputation, part 2: finite input streams
jessicata (jessica.liu.taylor) · 2020-02-17T03:51:57.238Z · score: 21 (5 votes) · comments (4)
[question] Wanting More Intellectual Stamina
mr.magpie · 2020-02-17T02:58:52.911Z · score: 5 (4 votes) · answers+comments (5)
Here is why most advice you hear that seems good, but "just doesn't work" from my unique perspective as a data scientist, as well as some that should actually work.
benf · 2020-02-17T02:58:42.109Z · score: 3 (4 votes) · comments (1)
[link] A Memetic Mediator Manifesto
Chris_Leong · 2020-02-17T02:14:56.683Z · score: 12 (3 votes) · comments (4)
UML XI: Nearest Neighbor Schemes
Rafael Harth (sil-ver) · 2020-02-16T20:30:14.112Z · score: 15 (4 votes) · comments (3)
[Link and commentary] The Offense-Defense Balance of Scientific Knowledge: Does Publishing AI Research Reduce Misuse?
MichaelA · 2020-02-16T19:56:15.963Z · score: 24 (7 votes) · comments (4)
Training Regime Day 2: Searching for bugs
Mark Xu (mark-xu) · 2020-02-16T17:16:32.606Z · score: 16 (9 votes) · comments (2)
Taking the Outgroup Seriously
Davis_Kingsley · 2020-02-16T13:23:42.645Z · score: 20 (15 votes) · comments (8)
On characterizing heavy-tailedness
Jsevillamol · 2020-02-16T00:14:06.197Z · score: 29 (11 votes) · comments (5)
Training Regime Day 1: What is applied rationality?
Mark Xu (mark-xu) · 2020-02-15T21:03:32.685Z · score: 23 (9 votes) · comments (3)
[question] It "wanted" ...
jmh · 2020-02-15T20:52:07.094Z · score: 4 (1 votes) · answers+comments (7)
Why Science is slowing down, Universities and Maslow's hierarchy of needs
George (George3d6) · 2020-02-15T20:39:36.559Z · score: 19 (16 votes) · comments (24)
← previous page (newer posts) · next page (older posts) →