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) →

The first future and the best future
KatjaGrace · 2024-04-25T06:40:04.510Z · comments (12)
Demystifying "Alignment" through a Comic
milanrosko · 2024-06-09T08:24:22.454Z · comments (19)
Skills I'd like my collaborators to have
Raemon · 2024-02-09T08:20:37.686Z · comments (9)
One Day Sooner
Screwtape · 2023-11-02T19:00:58.427Z · comments (7)
Picking Mentors For Research Programmes
Raymond D · 2023-11-10T13:01:14.197Z · comments (8)
Why I'm doing PauseAI
Joseph Miller (Josephm) · 2024-04-30T16:21:54.156Z · comments (16)
New LessWrong feature: Dialogue Matching
jacobjacob · 2023-11-16T21:27:16.763Z · comments (22)
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
Lucius Bushnaq (Lblack) · 2024-05-20T17:53:25.985Z · comments (4)
[link] A case for AI alignment being difficult
jessicata (jessica.liu.taylor) · 2023-12-31T19:55:26.130Z · comments (56)
New LessWrong review winner UI ("The LeastWrong" section and full-art post pages)
kave · 2024-02-28T02:42:05.801Z · comments (64)
On the future of language models
owencb · 2023-12-20T16:58:28.433Z · comments (17)
Scaling and evaluating sparse autoencoders
leogao · 2024-06-06T22:50:39.440Z · comments (6)
A bird's eye view of ARC's research
Jacob_Hilton · 2024-10-23T15:50:06.123Z · comments (12)
[link] My techno-optimism [By Vitalik Buterin]
habryka (habryka4) · 2023-11-27T23:53:35.859Z · comments (17)
In favour of exploring nagging doubts about x-risk
owencb · 2024-06-25T23:52:01.322Z · comments (2)
[question] What convincing warning shot could help prevent extinction from AI?
Charbel-Raphaël (charbel-raphael-segerie) · 2024-04-13T18:09:29.096Z · answers+comments (18)
Nonlinear’s Evidence: Debunking False and Misleading Claims
KatWoods (ea247) · 2023-12-12T13:16:12.008Z · comments (171)
Deception Chess: Game #1
Zane · 2023-11-03T21:13:55.777Z · comments (19)
Backdoors as an analogy for deceptive alignment
Jacob_Hilton · 2024-09-06T15:30:06.172Z · comments (2)
[link] Transformer Circuit Faithfulness Metrics Are Not Robust
Joseph Miller (Josephm) · 2024-07-12T03:47:30.077Z · comments (5)
SAE reconstruction errors are (empirically) pathological
wesg (wes-gurnee) · 2024-03-29T16:37:29.608Z · comments (16)
[link] Carl Sagan, nuking the moon, and not nuking the moon
eukaryote · 2024-04-13T04:08:50.166Z · comments (8)
Dreams of AI alignment: The danger of suggestive names
TurnTrout · 2024-02-10T01:22:51.715Z · comments (59)
[link] The Witness
Richard_Ngo (ricraz) · 2023-12-03T22:27:16.248Z · comments (4)
LLMs can learn about themselves by introspection
Felix J Binder (fjb) · 2024-10-18T16:12:51.231Z · comments (38)
[link] Poker is a bad game for teaching epistemics. Figgie is a better one.
rossry · 2024-07-08T06:05:20.459Z · comments (47)
What happens if you present 500 people with an argument that AI is risky?
KatjaGrace · 2024-09-04T16:40:03.562Z · comments (7)
[link] Notes from a Prompt Factory
Richard_Ngo (ricraz) · 2024-03-10T05:13:39.384Z · comments (19)
Lsusr's Rationality Dojo
lsusr · 2024-02-13T05:52:03.757Z · comments (17)
[link] A Chess-GPT Linear Emergent World Representation
Adam Karvonen (karvonenadam) · 2024-02-08T04:25:15.222Z · comments (14)
Response to nostalgebraist: proudly waving my moral-antirealist battle flag
Steven Byrnes (steve2152) · 2024-05-29T16:48:29.408Z · comments (29)
LLM Applications I Want To See
sarahconstantin · 2024-08-19T21:10:03.101Z · comments (5)
Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs
L Rudolf L (LRudL) · 2024-07-08T22:24:38.441Z · comments (28)
On Dwarksh’s Podcast with Leopold Aschenbrenner
Zvi · 2024-06-10T12:40:03.348Z · comments (7)
General Thoughts on Secular Solstice
Jeffrey Heninger (jeffrey-heninger) · 2024-03-23T18:48:43.940Z · comments (60)
[link] LessOnline (May 31—June 2, Berkeley, CA)
Ben Pace (Benito) · 2024-03-26T02:34:00.000Z · comments (24)
A simple model of math skill
Alex_Altair · 2024-07-21T18:57:33.697Z · comments (16)
Behavioral red-teaming is unlikely to produce clear, strong evidence that models aren't scheming
Buck · 2024-10-10T13:36:53.810Z · comments (2)
On the Executive Order
Zvi · 2023-11-01T14:20:01.657Z · comments (4)
[link] Advice for journalists
Nathan Young · 2024-10-07T16:46:40.929Z · comments (53)
[link] Advice for Activists from the History of Environmentalism
Jeffrey Heninger (jeffrey-heninger) · 2024-05-16T18:40:02.064Z · comments (8)
Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
Joseph Bloom (Jbloom) · 2024-02-02T06:54:53.392Z · comments (37)
[link] The Minority Faction
Richard_Ngo (ricraz) · 2024-06-24T20:01:27.436Z · comments (6)
[link] CIV: a story
Richard_Ngo (ricraz) · 2024-06-15T22:36:50.415Z · comments (6)
[link] My cover story in Jacobin on AI capitalism and the x-risk debates
garrison · 2024-02-12T23:34:16.526Z · comments (5)
Announcing the London Initiative for Safe AI (LISA)
James Fox · 2024-02-02T23:17:47.011Z · comments (0)
[link] "Deep Learning" Is Function Approximation
Zack_M_Davis · 2024-03-21T17:50:36.254Z · comments (28)
[Valence series] 1. Introduction
Steven Byrnes (steve2152) · 2023-12-04T15:40:21.274Z · comments (14)
Why comparative advantage does not help horses
Sherrinford · 2024-09-30T22:27:57.450Z · comments (10)
Learning-theoretic agenda reading list
Vanessa Kosoy (vanessa-kosoy) · 2023-11-09T17:25:35.046Z · comments (0)
← previous page (newer posts) · next page (older posts) →