LessWrong 2.0 Reader

View: New · Old · Top

Restrict date range: Today · This week · This month · Last three months · This year · All time

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

[link] Report on Frontier Model Training
YafahEdelman (yafah-edelman-1) · 2023-08-30T20:02:46.317Z · comments (21)
Choice Writings of Dominic Cummings
Connor_Flexman · 2021-10-13T02:41:44.291Z · comments (75)
What Comes After Epistemic Spot Checks?
Elizabeth (pktechgirl) · 2019-10-22T17:00:00.758Z · comments (9)
An Update on Academia vs. Industry (one year into my faculty job)
David Scott Krueger (formerly: capybaralet) (capybaralet) · 2022-09-03T20:43:37.701Z · comments (18)
Why I take short timelines seriously
NicholasKees (nick_kees) · 2024-01-28T22:27:21.098Z · comments (29)
How bad a future do ML researchers expect?
KatjaGrace · 2023-03-09T04:50:05.122Z · comments (7)
[question] What will 2040 probably look like assuming no singularity?
Daniel Kokotajlo (daniel-kokotajlo) · 2021-05-16T22:10:38.542Z · answers+comments (86)
A proposed method for forecasting transformative AI
Matthew Barnett (matthew-barnett) · 2023-02-10T19:34:01.358Z · comments (21)
Why I'm joining Anthropic
evhub · 2023-01-05T01:12:13.822Z · comments (4)
Ukraine Situation Report 2022/03/01
lsusr · 2022-03-02T05:07:59.763Z · comments (59)
[link] Gene drives: why the wait?
Metacelsus · 2022-09-19T23:37:17.595Z · comments (50)
Soares, Tallinn, and Yudkowsky discuss AGI cognition
So8res · 2021-11-29T19:26:33.232Z · comments (39)
LW Petrov Day 2022 (Monday, 9/26)
Ruby · 2022-09-22T02:56:19.738Z · comments (111)
My simple AGI investment & insurance strategy
lc · 2024-03-31T02:51:53.479Z · comments (20)
Omicron Variant Post #2
Zvi · 2021-11-29T16:30:01.368Z · comments (34)
Conversation with Eliezer: What do you want the system to do?
Akash (akash-wasil) · 2022-06-25T17:36:14.145Z · comments (38)
One-layer transformers aren’t equivalent to a set of skip-trigrams
Buck · 2023-02-17T17:26:13.819Z · comments (11)
Moloch and the sandpile catastrophe
Eric Raymond (eric-raymond) · 2022-04-02T15:35:12.552Z · comments (25)
Quintin's alignment papers roundup - week 1
Quintin Pope (quintin-pope) · 2022-09-10T06:39:01.773Z · comments (6)
[link] DontDoxScottAlexander.com - A Petition
Ben Pace (Benito) · 2020-06-25T05:44:50.050Z · comments (32)
Taking the parameters which seem to matter and rotating them until they don't
Garrett Baker (D0TheMath) · 2022-08-26T18:26:47.667Z · comments (48)
[link] Paper: LLMs trained on “A is B” fail to learn “B is A”
lberglund (brglnd) · 2023-09-23T19:55:53.427Z · comments (73)
[link] Responsible Scaling Policies Are Risk Management Done Wrong
simeon_c (WayZ) · 2023-10-25T23:46:34.247Z · comments (34)
Propagating Facts into Aesthetics
Raemon · 2019-12-19T04:09:17.816Z · comments (36)
Convincing All Capability Researchers
Logan Riggs (elriggs) · 2022-04-08T17:40:25.488Z · comments (70)
Compendium of problems with RLHF
Charbel-Raphaël (charbel-raphael-segerie) · 2023-01-29T11:40:53.147Z · comments (16)
My Understanding of Paul Christiano's Iterated Amplification AI Safety Research Agenda
Chi Nguyen · 2020-08-15T20:02:00.205Z · comments (20)
Stampy's AI Safety Info soft launch
steven0461 · 2023-10-05T22:13:04.632Z · comments (9)
Value Claims (In Particular) Are Usually Bullshit
johnswentworth · 2024-05-30T06:26:21.151Z · comments (18)
[link] Matt Levine on "Fraud is no fun without friends."
Raemon · 2021-01-19T18:23:20.614Z · comments (24)
Reward Is Not Enough
Steven Byrnes (steve2152) · 2021-06-16T13:52:33.745Z · comments (19)
[link] The Alignment Problem: Machine Learning and Human Values
Rohin Shah (rohinmshah) · 2020-10-06T17:41:21.138Z · comments (7)
Natural Latents: The Math
johnswentworth · 2023-12-27T19:03:01.923Z · comments (31)
Land Ho!
Zvi · 2022-01-20T13:30:01.262Z · comments (4)
Harms and possibilities of schooling
TsviBT · 2022-02-22T07:48:09.542Z · comments (38)
[link] Introducing the Center for AI Policy (& we're hiring!)
Thomas Larsen (thomas-larsen) · 2023-08-28T21:17:11.703Z · comments (50)
Problem relaxation as a tactic
TurnTrout · 2020-04-22T23:44:42.398Z · comments (8)
Perpetual Dickensian Poverty?
jefftk (jkaufman) · 2021-12-21T13:30:03.543Z · comments (18)
Delta Strain: Fact Dump and Some Policy Takeaways
Connor_Flexman · 2021-07-28T03:38:34.455Z · comments (60)
Future ML Systems Will Be Qualitatively Different
jsteinhardt · 2022-01-11T19:50:11.377Z · comments (10)
How to Bounded Distrust
Zvi · 2023-01-09T13:10:00.942Z · comments (15)
FHI paper published in Science: interventions against COVID-19
SoerenMind · 2020-12-16T21:19:00.441Z · comments (0)
Unwitting cult leaders
Kaj_Sotala · 2021-02-11T11:10:04.504Z · comments (9)
Geometric Exploration, Arithmetic Exploitation
Scott Garrabrant · 2022-11-24T15:36:30.334Z · comments (4)
Christiano, Cotra, and Yudkowsky on AI progress
Eliezer Yudkowsky (Eliezer_Yudkowsky) · 2021-11-25T16:45:32.482Z · comments (95)
Solving the Mechanistic Interpretability challenges: EIS VII Challenge 1
StefanHex (Stefan42) · 2023-05-09T19:41:10.528Z · comments (1)
My Effortless Weightloss Story: A Quick Runthrough
CuoreDiVetro · 2023-09-30T23:02:45.128Z · comments (77)
Late 2021 MIRI Conversations: AMA / Discussion
Rob Bensinger (RobbBB) · 2022-02-28T20:03:05.318Z · comments (199)
"Zero Sum" is a misnomer.
abramdemski · 2020-09-30T18:25:30.603Z · comments (34)
RTFB: On the New Proposed CAIP AI Bill
Zvi · 2024-04-10T18:30:08.410Z · comments (14)
← previous page (newer posts) · next page (older posts) →