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) →

Could randomly choosing people to serve as representatives lead to better government?
John Huang · 2024-10-21T17:10:20.920Z · comments (13)
My guess at Conjecture's vision: triggering a narrative bifurcation
Alexandre Variengien (alexandre-variengien) · 2024-02-06T19:10:42.690Z · comments (12)
Q&A on Proposed SB 1047
Zvi · 2024-05-02T15:10:02.916Z · comments (8)
(Not) Derailing the LessOnline Puzzle Hunt
Error · 2024-06-04T01:28:31.688Z · comments (2)
Interpretability with Sparse Autoencoders (Colab exercises)
CallumMcDougall (TheMcDouglas) · 2023-11-29T12:56:21.608Z · comments (9)
Idealized Agents Are Approximate Causal Mirrors (+ Radical Optimism on Agent Foundations)
Thane Ruthenis · 2023-12-22T20:19:13.865Z · comments (14)
Interpreting Preference Models w/ Sparse Autoencoders
Logan Riggs (elriggs) · 2024-07-01T21:35:40.603Z · comments (12)
SAE-VIS: Announcement Post
CallumMcDougall (TheMcDouglas) · 2024-03-31T15:30:49.079Z · comments (8)
Introducing Transluce — A Letter from the Founders
jsteinhardt · 2024-10-23T18:10:02.526Z · comments (2)
[link] MIRI's June 2024 Newsletter
Harlan · 2024-06-14T23:02:23.721Z · comments (18)
Mistakes people make when thinking about units
Isaac King (KingSupernova) · 2024-06-25T03:39:20.138Z · comments (14)
Neural uncertainty estimation review article (for alignment)
Charlie Steiner · 2023-12-05T08:01:32.723Z · comments (3)
Anthropic Fall 2023 Debate Progress Update
Ansh Radhakrishnan (anshuman-radhakrishnan-1) · 2023-11-28T05:37:30.070Z · comments (9)
A Simple Toy Coherence Theorem
johnswentworth · 2024-08-02T17:47:50.642Z · comments (19)
On Dwarkesh’s Podcast with OpenAI’s John Schulman
Zvi · 2024-05-21T17:30:04.332Z · comments (4)
Joshua Achiam Public Statement Analysis
Zvi · 2024-10-10T12:50:06.285Z · comments (14)
[link] Soft Nationalization: how the USG will control AI labs
Deric Cheng (deric-cheng) · 2024-08-27T15:11:14.601Z · comments (7)
The World in 2029
Nathan Young · 2024-03-02T18:03:29.368Z · comments (37)
[question] Interest in Leetcode, but for Rationality?
Gregory (gregory-eales) · 2024-10-16T17:54:25.578Z · answers+comments (20)
A Gentle Introduction to Risk Frameworks Beyond Forecasting
pendingsurvival · 2024-04-11T18:03:25.605Z · comments (10)
[Full Post] Progress Update #1 from the GDM Mech Interp Team
Neel Nanda (neel-nanda-1) · 2024-04-19T19:06:59.185Z · comments (10)
[link] Nick Bostrom’s new book, “Deep Utopia”, is out today
PeterH · 2024-03-27T11:24:01.401Z · comments (5)
Scalable Oversight and Weak-to-Strong Generalization: Compatible approaches to the same problem
Ansh Radhakrishnan (anshuman-radhakrishnan-1) · 2023-12-16T05:49:23.672Z · comments (3)
[link] A Narrow Path: a plan to deal with AI extinction risk
Andrea_Miotti (AndreaM) · 2024-10-07T13:02:15.229Z · comments (11)
Companies' safety plans neglect risks from scheming AI
Zach Stein-Perlman · 2024-06-03T15:00:20.236Z · comments (4)
AI for Bio: State Of The Field
sarahconstantin · 2024-08-30T18:00:02.187Z · comments (2)
The One and a Half Gemini
Zvi · 2024-02-22T13:10:04.725Z · comments (4)
Prompts for Big-Picture Planning
Raemon · 2024-04-13T03:04:24.523Z · comments (1)
Announcing Suffering For Good
Garrett Baker (D0TheMath) · 2024-04-01T17:08:12.322Z · comments (5)
AI #92: Behind the Curve
Zvi · 2024-11-28T14:40:05.448Z · comments (4)
Do sparse autoencoders find "true features"?
Demian Till · 2024-02-22T18:06:59.630Z · comments (33)
[link] LK-99 in retrospect
bhauth · 2024-07-07T02:06:27.660Z · comments (21)
AXRP Episode 31 - Singular Learning Theory with Daniel Murfet
DanielFilan · 2024-05-07T03:50:05.001Z · comments (4)
The case for a negative alignment tax
Cameron Berg (cameron-berg) · 2024-09-18T18:33:18.491Z · comments (20)
D&D.Sci Scenario Index
aphyer · 2024-07-23T02:00:43.483Z · comments (0)
[link] Excerpts from "A Reader's Manifesto"
Arjun Panickssery (arjun-panickssery) · 2024-09-06T22:37:40.254Z · comments (1)
When "yang" goes wrong
Joe Carlsmith (joekc) · 2024-01-08T16:35:50.607Z · comments (6)
Claude 3 claims it's conscious, doesn't want to die or be modified
Mikhail Samin (mikhail-samin) · 2024-03-04T23:05:00.376Z · comments (113)
In Defense of Open-Minded UDT
abramdemski · 2024-08-12T18:27:36.220Z · comments (27)
Guide to SB 1047
Zvi · 2024-08-20T13:10:07.408Z · comments (18)
LW Frontpage Experiments! (aka "Take the wheel, Shoggoth!")
Ruby · 2024-04-23T03:58:43.443Z · comments (27)
FarmKind's Illusory Offer
jefftk (jkaufman) · 2024-08-09T11:30:07.082Z · comments (5)
Survey for alignment researchers!
Cameron Berg (cameron-berg) · 2024-02-02T20:41:44.323Z · comments (11)
We need a Science of Evals
Marius Hobbhahn (marius-hobbhahn) · 2024-01-22T20:30:39.493Z · comments (13)
The Mask Comes Off: At What Price?
Zvi · 2024-10-21T23:50:05.247Z · comments (16)
[link] If far-UV is so great, why isn't it everywhere?
Austin Chen (austin-chen) · 2024-10-19T18:56:58.910Z · comments (23)
Instruction-following AGI is easier and more likely than value aligned AGI
Seth Herd · 2024-05-15T19:38:03.185Z · comments (25)
“Artificial General Intelligence”: an extremely brief FAQ
Steven Byrnes (steve2152) · 2024-03-11T17:49:02.496Z · comments (6)
[link] Yoshua Bengio: Reasoning through arguments against taking AI safety seriously
Judd Rosenblatt (judd) · 2024-07-11T23:53:17.187Z · comments (3)
Adam Optimizer Causes Privileged Basis in Transformer LM Residual Stream
Diego Caples (diego-caples) · 2024-09-06T17:55:34.265Z · comments (7)
← previous page (newer posts) · next page (older posts) →