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) →

Are we in an AI overhang?
Andy Jones (andyljones) · 2020-07-27T12:48:05.196Z · comments (106)
DARPA Digital Tutor: Four Months to Total Technical Expertise?
JohnBuridan · 2020-07-06T23:34:21.089Z · comments (21)
Six economics misconceptions of mine which I've resolved over the last few years
Buck · 2020-07-13T03:01:43.717Z · comments (59)
Limits of Current US Prediction Markets (PredictIt Case Study)
aphyer · 2020-07-14T07:24:23.421Z · comments (48)
[link] Thiel on Progress and Stagnation
Richard_Ngo (ricraz) · 2020-07-20T20:27:59.112Z · comments (32)
Swiss Political System: More than You ever Wanted to Know (I.)
Martin Sustrik (sustrik) · 2020-07-19T01:11:54.756Z · comments (39)
Rereading Atlas Shrugged
Vaniver · 2020-07-28T18:54:45.272Z · comments (36)
"Can you keep this confidential? How do you know?"
Raemon · 2020-07-21T00:33:27.974Z · comments (41)
Developmental Stages of GPTs
orthonormal · 2020-07-26T22:03:19.588Z · comments (71)
Situating LessWrong in contemporary philosophy: An interview with Jon Livengood
Suspended Reason (suspended-reason) · 2020-07-01T00:37:00.695Z · comments (21)
Can you get AGI from a Transformer?
Steven Byrnes (steve2152) · 2020-07-23T15:27:51.712Z · comments (40)
Alignment As A Bottleneck To Usefulness Of GPT-3
johnswentworth · 2020-07-21T20:02:36.030Z · comments (57)
Solving Math Problems by Relay
bgold · 2020-07-17T15:32:00.985Z · comments (26)
Classifying games like the Prisoner's Dilemma
philh · 2020-07-04T17:10:01.965Z · comments (28)
Kelly Bet on Everything
Jacob Falkovich (Jacobian) · 2020-07-10T02:48:12.868Z · comments (20)
Attention is your scarcest resource
benkuhn · 2020-07-30T01:00:13.705Z · comments (2)
Learning the prior
paulfchristiano · 2020-07-05T21:00:01.192Z · comments (28)
Reveal Culture
MalcolmOcean (malcolmocean) · 2020-07-25T03:36:28.525Z · comments (18)
Swiss Political System: More than You ever Wanted to Know (II.)
Martin Sustrik (sustrik) · 2020-07-22T13:50:04.033Z · comments (24)
[link] Collection of GPT-3 results
Kaj_Sotala · 2020-07-18T20:04:50.027Z · comments (24)
Covid 7/2: It Could Be Worse
Zvi · 2020-07-02T20:20:01.045Z · comments (13)
Be impatient
benkuhn · 2020-07-24T01:30:06.341Z · comments (5)
High Stock Prices Make Sense Right Now
johnswentworth · 2020-07-03T20:16:53.852Z · comments (27)
Covid 7/16: Becoming the Mask
Zvi · 2020-07-16T12:40:00.663Z · comments (20)
Competition: Amplify Rohin’s Prediction on AGI researchers & Safety Concerns
stuhlmueller · 2020-07-21T20:06:09.194Z · comments (40)
Your Prioritization is Underspecified
romeostevensit · 2020-07-10T20:48:29.654Z · comments (13)
How good is humanity at coordination?
Buck · 2020-07-21T20:01:39.744Z · comments (44)
What counts as defection?
TurnTrout · 2020-07-12T22:03:39.261Z · comments (21)
What Failure Looks Like: Distilling the Discussion
Ben Pace (Benito) · 2020-07-29T21:49:17.255Z · comments (14)
The Goldbach conjecture is probably correct; so was Fermat's last theorem
Stuart_Armstrong · 2020-07-14T19:30:14.806Z · comments (27)
PSA: Tagging is Awesome
abramdemski · 2020-07-30T17:52:14.047Z · comments (19)
What a 20-year-lead in military tech might look like
Daniel Kokotajlo (daniel-kokotajlo) · 2020-07-29T20:10:09.303Z · comments (47)
[question] How "honest" is GPT-3?
abramdemski · 2020-07-08T19:38:01.800Z · answers+comments (18)
Criticism of some popular LW articles
DirectedEvolution (AllAmericanBreakfast) · 2020-07-19T01:16:50.230Z · comments (19)
[question] To what extent is GPT-3 capable of reasoning?
TurnTrout · 2020-07-20T17:10:50.265Z · answers+comments (73)
The Basic Double Crux pattern
Eli Tyre (elityre) · 2020-07-22T06:41:28.130Z · comments (21)
Tagging Open Call / Discussion Thread
Ruby · 2020-07-28T21:58:25.087Z · comments (118)
Better priors as a safety problem
paulfchristiano · 2020-07-05T21:20:02.851Z · comments (7)
What Would I Do? Self-prediction in Simple Algorithms
Scott Garrabrant · 2020-07-20T04:27:25.490Z · comments (12)
Mazes and Duality
johnswentworth · 2020-07-14T19:54:42.479Z · comments (10)
Arguments against myopic training
Richard_Ngo (ricraz) · 2020-07-09T16:07:27.681Z · comments (39)
[link] AI Research Considerations for Human Existential Safety (ARCHES)
habryka (habryka4) · 2020-07-09T02:49:27.267Z · comments (7)
Covid 7/23: The Second Summit
Zvi · 2020-07-23T14:40:00.980Z · comments (6)
Lessons on AI Takeover from the conquistadors
Daniel Kokotajlo (daniel-kokotajlo) · 2020-07-17T22:35:32.265Z · comments (31)
The Equation of Knowledge
Lê Nguyên Hoang (le-nguyen-hoang-1) · 2020-07-07T16:09:10.367Z · comments (3)
Covid 7/9: Lies, Damn Lies and Death Rates
Zvi · 2020-07-09T13:40:01.359Z · comments (16)
[link] $1000 bounty for OpenAI to show whether GPT3 was "deliberately" pretending to be stupider than it is
jacobjacob · 2020-07-21T18:42:44.704Z · comments (39)
A space of proposals for building safe advanced AI
Richard_Ngo (ricraz) · 2020-07-10T16:58:33.566Z · comments (4)
What does it mean to apply decision theory?
abramdemski · 2020-07-08T20:31:05.884Z · comments (5)
[link] Become a person who Actually Does Things
Neel Nanda (neel-nanda-1) · 2020-07-25T09:29:21.314Z · comments (17)
next page (older posts) →