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) →

(The) Lightcone is nothing without its people: LW + Lighthaven's big fundraiser
habryka (habryka4) · 2024-11-30T02:55:16.077Z · comments (212)
OpenAI Email Archives (from Musk v. Altman and OpenAI blog)
habryka (habryka4) · 2024-11-16T06:38:03.937Z · comments (80)
Alignment Faking in Large Language Models
ryan_greenblatt · 2024-12-18T17:19:06.665Z · comments (53)
The hostile telepaths problem
Valentine · 2024-10-27T15:26:53.610Z · comments (84)
[link] Survival without dignity
L Rudolf L (LRudL) · 2024-11-04T02:29:38.758Z · comments (28)
[link] I got dysentery so you don’t have to
eukaryote · 2024-10-22T04:55:58.422Z · comments (4)
[link] Biological risk from the mirror world
jasoncrawford · 2024-12-12T19:07:06.305Z · comments (29)
The Online Sports Gambling Experiment Has Failed
Zvi · 2024-11-11T14:30:04.371Z · comments (28)
You are not too "irrational" to know your preferences.
DaystarEld · 2024-11-26T15:01:42.996Z · comments (50)
Ayn Rand’s model of “living money”; and an upside of burnout
AnnaSalamon · 2024-11-16T02:59:07.368Z · comments (58)
[link] What TMS is like
Sable · 2024-10-31T00:44:22.612Z · comments (23)
Frontier Models are Capable of In-context Scheming
Marius Hobbhahn (marius-hobbhahn) · 2024-12-05T22:11:17.320Z · comments (24)
Making a conservative case for alignment
Cameron Berg (cameron-berg) · 2024-11-15T18:55:40.864Z · comments (68)
[link] Understanding Shapley Values with Venn Diagrams
Carson L · 2024-12-06T21:56:43.960Z · comments (32)
What Goes Without Saying
sarahconstantin · 2024-12-20T18:00:06.363Z · comments (9)
[link] The Compendium, A full argument about extinction risk from AGI
adamShimi · 2024-10-31T12:01:51.714Z · comments (52)
Communications in Hard Mode (My new job at MIRI)
tanagrabeast · 2024-12-13T20:13:44.825Z · comments (23)
Information vs Assurance
johnswentworth · 2024-10-20T23:16:25.762Z · comments (17)
Orienting to 3 year AGI timelines
Nikola Jurkovic (nikolaisalreadytaken) · 2024-12-22T01:15:11.401Z · comments (25)
[link] Overcoming Bias Anthology
Arjun Panickssery (arjun-panickssery) · 2024-10-20T02:01:23.463Z · comments (14)
The Median Researcher Problem
johnswentworth · 2024-11-02T20:16:11.341Z · comments (69)
o1 is a bad idea
abramdemski · 2024-11-11T21:20:24.892Z · comments (38)
The Summoned Heroine's Prediction Markets Keep Providing Financial Services To The Demon King!
abstractapplic · 2024-10-26T12:34:51.059Z · comments (16)
Neutrality
sarahconstantin · 2024-11-13T23:10:05.469Z · comments (27)
Current safety training techniques do not fully transfer to the agent setting
Simon Lermen (dalasnoin) · 2024-11-03T19:24:51.537Z · comments (8)
[link] Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
cloud · 2024-12-06T22:19:26.717Z · comments (12)
"It's a 10% chance which I did 10 times, so it should be 100%"
egor.timatkov · 2024-11-18T01:14:27.738Z · comments (57)
A Rocket–Interpretability Analogy
plex (ete) · 2024-10-21T13:55:18.184Z · comments (31)
o3
Zach Stein-Perlman · 2024-12-20T18:30:29.448Z · comments (144)
“Alignment Faking” frame is somewhat fake
Jan_Kulveit · 2024-12-20T09:51:04.664Z · comments (13)
[link] Arithmetic is an underrated world-modeling technology
dynomight · 2024-10-17T14:00:22.475Z · comments (32)
Repeal the Jones Act of 1920
Zvi · 2024-11-27T15:00:06.801Z · comments (23)
[link] o1: A Technical Primer
Jesse Hoogland (jhoogland) · 2024-12-09T19:09:12.413Z · comments (17)
[link] China Hawks are Manufacturing an AI Arms Race
garrison · 2024-11-20T18:17:51.958Z · comments (42)
[link] When Is Insurance Worth It?
kqr · 2024-12-19T19:07:32.573Z · comments (51)
Subskills of "Listening to Wisdom"
Raemon · 2024-12-09T03:01:18.706Z · comments (16)
[question] Which things were you surprised to learn are not metaphors?
Eric Neyman (UnexpectedValues) · 2024-11-21T18:56:18.025Z · answers+comments (79)
"The Solomonoff Prior is Malign" is a special case of a simpler argument
David Matolcsi (matolcsid) · 2024-11-17T21:32:34.711Z · comments (44)
[link] OpenAI's CBRN tests seem unclear
LucaRighetti (Error404Dinosaur) · 2024-11-21T17:28:30.290Z · comments (6)
Why Don't We Just... Shoggoth+Face+Paraphraser?
Daniel Kokotajlo (daniel-kokotajlo) · 2024-11-19T20:53:52.084Z · comments (51)
BIG-Bench Canary Contamination in GPT-4
Jozdien · 2024-10-22T15:40:48.166Z · comments (13)
A bird's eye view of ARC's research
Jacob_Hilton · 2024-10-23T15:50:06.123Z · comments (12)
[link] The Dangers of Mirrored Life
Niko_McCarty (niko-2) · 2024-12-12T20:58:32.750Z · comments (7)
[link] Miles Brundage resigned from OpenAI, and his AGI readiness team was disbanded
garrison · 2024-10-23T23:40:57.180Z · comments (1)
Passages I Highlighted in The Letters of J.R.R.Tolkien
Ivan Vendrov (ivan-vendrov) · 2024-11-25T01:47:59.071Z · comments (10)
The Dream Machine
sarahconstantin · 2024-12-05T00:00:05.796Z · comments (6)
The o1 System Card Is Not About o1
Zvi · 2024-12-13T20:30:08.048Z · comments (5)
What o3 Becomes by 2028
Vladimir_Nesov · 2024-12-22T12:37:20.929Z · comments (10)
Scissors Statements for President?
AnnaSalamon · 2024-11-06T10:38:21.230Z · comments (31)
Should CA, TX, OK, and LA merge into a giant swing state, just for elections?
Thomas Kwa (thomas-kwa) · 2024-11-06T23:01:48.992Z · comments (35)
next page (older posts) →