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) →

[Completed] The 2024 Petrov Day Scenario
Ben Pace (Benito) · 2024-09-26T08:08:32.495Z · comments (114)
"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)
Circuits in Superposition: Compressing many small neural networks into one
Lucius Bushnaq (Lblack) · 2024-10-14T13:06:14.596Z · comments (8)
BIG-Bench Canary Contamination in GPT-4
Jozdien · 2024-10-22T15:40:48.166Z · comments (13)
[link] Miles Brundage resigned from OpenAI, and his AGI readiness team was disbanded
garrison · 2024-10-23T23:40:57.180Z · comments (1)
[link] My Number 1 Epistemology Book Recommendation: Inventing Temperature
adamShimi · 2024-09-08T14:30:40.456Z · comments (18)
A bird's eye view of ARC's research
Jacob_Hilton · 2024-10-23T15:50:06.123Z · comments (12)
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)
Why I funded PIBBSS
Ryan Kidd (ryankidd44) · 2024-09-15T19:56:33.018Z · comments (21)
[link] OpenAI's CBRN tests seem unclear
LucaRighetti (Error404Dinosaur) · 2024-11-21T17:28:30.290Z · comments (6)
Scissors Statements for President?
AnnaSalamon · 2024-11-06T10:38:21.230Z · comments (31)
DeepSeek beats o1-preview on math, ties on coding; will release weights
Zach Stein-Perlman · 2024-11-20T23:50:26.597Z · comments (12)
[link] Announcing turntrout.com, my new digital home
TurnTrout · 2024-11-17T17:42:08.164Z · comments (22)
Why Don't We Just... Shoggoth+Face+Paraphraser?
Daniel Kokotajlo (daniel-kokotajlo) · 2024-11-19T20:53:52.084Z · comments (43)
Backdoors as an analogy for deceptive alignment
Jacob_Hilton · 2024-09-06T15:30:06.172Z · comments (2)
I turned decision theory problems into memes about trolleys
Tapatakt · 2024-10-30T20:13:29.589Z · comments (20)
What happens if you present 500 people with an argument that AI is risky?
KatjaGrace · 2024-09-04T16:40:03.562Z · comments (7)
Refactoring cryonics as structural brain preservation
Andy_McKenzie · 2024-09-11T18:36:30.285Z · comments (14)
LLMs can learn about themselves by introspection
Felix J Binder (fjb) · 2024-10-18T16:12:51.231Z · comments (38)
[link] Advice for journalists
Nathan Young · 2024-10-07T16:46:40.929Z · comments (53)
Behavioral red-teaming is unlikely to produce clear, strong evidence that models aren't scheming
Buck · 2024-10-10T13:36:53.810Z · comments (4)
Why comparative advantage does not help horses
Sherrinford · 2024-09-30T22:27:57.450Z · comments (10)
The case for unlearning that removes information from LLM weights
Fabien Roger (Fabien) · 2024-10-14T14:08:04.775Z · comments (14)
[link] Seven lessons I didn't learn from election day
Eric Neyman (UnexpectedValues) · 2024-11-14T18:39:07.053Z · comments (33)
Information vs Assurance
johnswentworth · 2024-10-20T23:16:25.762Z · comments (7)
[link] Sabotage Evaluations for Frontier Models
David Duvenaud (david-duvenaud) · 2024-10-18T22:33:14.320Z · comments (55)
[link] Finishing The SB-1047 Documentary In 6 Weeks
Michaël Trazzi (mtrazzi) · 2024-10-28T20:17:47.465Z · comments (5)
You can, in fact, bamboozle an unaligned AI into sparing your life
David Matolcsi (matolcsid) · 2024-09-29T16:59:43.942Z · comments (171)
2024 Petrov Day Retrospective
Ben Pace (Benito) · 2024-09-28T21:30:14.952Z · comments (25)
[question] What are the best arguments for/against AIs being "slightly 'nice'"?
Raemon · 2024-09-24T02:00:19.605Z · answers+comments (54)
[link] Anthropic: Three Sketches of ASL-4 Safety Case Components
Zach Stein-Perlman · 2024-11-06T16:00:06.940Z · comments (33)
[link] Executable philosophy as a failed totalizing meta-worldview
jessicata (jessica.liu.taylor) · 2024-09-04T22:50:18.294Z · comments (40)
Science advances one funeral at a time
Cameron Berg (cameron-berg) · 2024-11-01T23:06:19.381Z · comments (9)
[question] Am I confused about the "malign universal prior" argument?
nostalgebraist · 2024-08-27T23:17:22.779Z · answers+comments (33)
SB 1047: Final Takes and Also AB 3211
Zvi · 2024-08-27T22:10:07.647Z · comments (11)
[link] China Hawks are Manufacturing an AI Arms Race
garrison · 2024-11-20T18:17:51.958Z · comments (13)
Bigger Livers?
sarahconstantin · 2024-11-08T21:50:09.814Z · comments (10)
Catastrophic sabotage as a major threat model for human-level AI systems
evhub · 2024-10-22T20:57:11.395Z · comments (8)
LLMs Look Increasingly Like General Reasoners
eggsyntax · 2024-11-08T23:47:28.886Z · comments (45)
Singular learning theory: exercises
Zach Furman (zfurman) · 2024-08-30T20:00:03.785Z · comments (5)
Anvil Problems
Screwtape · 2024-11-13T22:57:41.974Z · comments (12)
Three Notions of "Power"
johnswentworth · 2024-10-30T06:10:08.326Z · comments (43)
[Intuitive self-models] 1. Preliminaries
Steven Byrnes (steve2152) · 2024-09-19T13:45:27.976Z · comments (20)
[link] Self-Help Corner: Loop Detection
adamShimi · 2024-10-02T08:33:23.487Z · comments (6)
Solving adversarial attacks in computer vision as a baby version of general AI alignment
Stanislav Fort (stanislavfort) · 2024-08-29T17:17:47.136Z · comments (8)
Research update: Towards a Law of Iterated Expectations for Heuristic Estimators
Eric Neyman (UnexpectedValues) · 2024-10-07T19:29:29.033Z · comments (2)
There is a globe in your LLM
jacob_drori (jacobcd52) · 2024-10-08T00:43:40.300Z · comments (4)
GPT-o1
Zvi · 2024-09-16T13:40:06.236Z · comments (34)
"The Solomonoff Prior is Malign" is a special case of a simpler argument
David Matolcsi (matolcsid) · 2024-11-17T21:32:34.711Z · comments (23)
5 homegrown EA projects, seeking small donors
Austin Chen (austin-chen) · 2024-10-28T23:24:25.745Z · comments (4)
← previous page (newer posts) · next page (older posts) →