LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

AGI safety from first principles: Alignment
Richard_Ngo (ricraz) · 2020-10-01T03:13:46.491Z · comments (3)
[question] Babble challenge: 50 ways of sending something to the moon
jacobjacob · 2020-10-01T04:20:24.016Z · answers+comments (114)
Forecasting Newsletter: September 2020.
NunoSempere (Radamantis) · 2020-10-01T11:00:54.354Z · comments (3)
Three car seats?
jefftk (jkaufman) · 2020-10-01T14:30:06.216Z · comments (9)
[link] Your Standards are Too High
Neel Nanda (neel-nanda-1) · 2020-10-01T17:03:31.969Z · comments (2)
Words and Implications
johnswentworth · 2020-10-01T17:37:20.399Z · comments (25)
Covid 10/1: The Long Haul
Zvi · 2020-10-01T18:00:00.848Z · comments (22)
Hiring engineers and researchers to help align GPT-3
paulfchristiano · 2020-10-01T18:54:23.551Z · comments (13)
Open & Welcome Thread – October 2020
Ben Pace (Benito) · 2020-10-01T19:06:45.928Z · comments (54)
Linkpost: Choice Explains Positivity and Confirmation Bias
Gunnar_Zarncke · 2020-10-01T21:46:46.289Z · comments (0)
Sunday Meetup: Workshop on Online Surveys with Spencer Greenberg
Raemon · 2020-10-02T00:34:35.586Z · comments (5)
A simple device for indoor air management
Richard Korzekwa (Grothor) · 2020-10-02T01:02:42.471Z · comments (10)
Math That Clicks: Look for Two-Way Correspondences
TurnTrout · 2020-10-02T01:22:18.177Z · comments (4)
Attention to snakes not fear of snakes: evolution encoding environmental knowledge in peripheral systems
Kaj_Sotala · 2020-10-02T11:50:05.327Z · comments (1)
Muting on Group Calls
jefftk (jkaufman) · 2020-10-02T20:30:11.280Z · comments (2)
AGI safety from first principles: Control
Richard_Ngo (ricraz) · 2020-10-02T21:51:20.649Z · comments (6)
[link] On Option Paralysis - The Thing You Actually Do
Neel Nanda (neel-nanda-1) · 2020-10-03T11:50:57.070Z · comments (5)
Weird Things About Money
abramdemski · 2020-10-03T17:13:48.772Z · comments (31)
Postmortem to Petrov Day, 2020
Ben Pace (Benito) · 2020-10-03T21:30:56.491Z · comments (63)
Fishbowl reality
Elo · 2020-10-04T02:16:18.595Z · comments (0)
[question] Is there any work on incorporating aleatoric uncertainty and/or inherent randomness into AIXI?
David Scott Krueger (formerly: capybaralet) (capybaralet) · 2020-10-04T08:10:56.400Z · answers+comments (7)
Public transmit metta
Kaj_Sotala · 2020-10-04T11:40:03.879Z · comments (6)
AI race considerations in a report by the U.S. House Committee on Armed Services
NunoSempere (Radamantis) · 2020-10-04T12:11:36.129Z · comments (4)
[question] One hub, or many?
abramdemski · 2020-10-04T16:58:40.800Z · answers+comments (12)
[question] What reacts would you like to be able to give on posts? (emoticons, cognicons, and more)
Mati_Roy (MathieuRoy) · 2020-10-04T18:31:06.596Z · answers+comments (27)
[Link] Faster than Light in Our Model of Physics: Some Preliminary Thoughts—Stephen Wolfram Writings
Kenny · 2020-10-04T20:26:51.611Z · comments (14)
AGI safety from first principles: Conclusion
Richard_Ngo (ricraz) · 2020-10-04T23:06:58.975Z · comments (6)
[question] Rationality and Climate Change
Emiya (andrea-mulazzani) · 2020-10-05T10:21:09.512Z · answers+comments (76)
Universal Eudaimonia
hg00 · 2020-10-05T13:45:19.609Z · comments (6)
The Felt Sense: What, Why and How
Kaj_Sotala · 2020-10-05T15:57:50.545Z · comments (23)
COVID Strategy 101
Mike Harris (mike-harris-1) · 2020-10-05T19:30:43.529Z · comments (7)
Domains of truth
mxln · 2020-10-05T19:46:28.843Z · comments (1)
[link] The Rise and Fall of American Growth: A summary
jasoncrawford · 2020-10-05T21:41:08.447Z · comments (9)
[question] Fermi Challenge: Trains and Air Cargo
Ben Pace (Benito) · 2020-10-05T21:51:45.281Z · answers+comments (21)
Not Even Evidence
Dach · 2020-10-06T01:20:25.028Z · comments (15)
Conversations from inside early singularity
faint reminder · 2020-10-06T16:46:44.738Z · comments (0)
Large Effects Can't Prove Small Causes
Bucky · 2020-10-06T17:34:24.153Z · comments (1)
[link] The Alignment Problem: Machine Learning and Human Values
Rohin Shah (rohinmshah) · 2020-10-06T17:41:21.138Z · comments (7)
Forcing Freedom
vlad.proex · 2020-10-06T18:15:13.596Z · comments (12)
Can we hold intellectuals to similar public standards as athletes?
ozziegooen · 2020-10-07T04:22:20.450Z · comments (48)
Buying micro-biostasis
Mati_Roy (MathieuRoy) · 2020-10-07T10:55:19.006Z · comments (1)
[question] Brainstorming positive visions of AI
jungofthewon · 2020-10-07T16:09:33.453Z · answers+comments (24)
[question] How worried are the relevant experts about a magnetic pole reversal?
Sunny from QAD (Evan Rysdam) · 2020-10-07T16:19:51.607Z · answers+comments (4)
[link] Open Communication in the Days of Malicious Online Actors
ozziegooen · 2020-10-07T16:30:01.935Z · comments (10)
[question] Inaccessible finely tuned RNG in humans?
Sandi · 2020-10-07T17:04:36.142Z · answers+comments (13)
[AN #120]: Tracing the intellectual roots of AI and AI alignment
Rohin Shah (rohinmshah) · 2020-10-07T17:10:07.013Z · comments (4)
[link] Review and Summary of 'Moral Uncertainty'
fin · 2020-10-07T17:52:42.189Z · comments (7)
[question] How can an AI demonstrate purely through chat that it is an AI, and not a human?
hugh.mann · 2020-10-07T17:53:07.715Z · answers+comments (4)
Lessons on Value of Information From Civ
johnswentworth · 2020-10-07T18:18:40.118Z · comments (6)
Thoughts on ADHD
romeostevensit · 2020-10-07T20:46:24.827Z · comments (16)
next page (older posts) →