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] Rational Animations' intro to mechanistic interpretability
Writer · 2024-06-14T16:10:57.015Z · comments (1)
Some open-source dictionaries and dictionary learning infrastructure
Sam Marks (samuel-marks) · 2023-12-05T06:05:21.903Z · comments (7)
The Gemini Incident Continues
Zvi · 2024-02-27T16:00:05.648Z · comments (6)
Work with me on agent foundations: independent fellowship
Alex_Altair · 2024-09-21T13:59:16.706Z · comments (5)
We Don't Know Our Own Values, but Reward Bridges The Is-Ought Gap
johnswentworth · 2024-09-19T22:22:05.307Z · comments (47)
AI #80: Never Have I Ever
Zvi · 2024-09-10T17:50:08.074Z · comments (20)
Dating Roundup #3: Third Time’s the Charm
Zvi · 2024-05-08T13:30:03.232Z · comments (26)
A starting point for making sense of task structure (in machine learning)
Kaarel (kh) · 2024-02-24T01:51:49.227Z · comments (2)
[link] How people stopped dying from diarrhea so much (& other life-saving decisions)
Writer · 2024-03-16T16:00:47.830Z · comments (0)
Atlantis: Berkeley event venue available for rent
Jonas V (Jonas Vollmer) · 2023-11-22T01:47:12.026Z · comments (0)
Things Solenoid Narrates
Solenoid_Entity · 2024-04-12T23:57:16.169Z · comments (2)
[link] AlphaGeometry: An Olympiad-level AI system for geometry
alyssavance · 2024-01-17T17:17:30.913Z · comments (9)
[link] I'd also take $7 trillion
bhauth · 2024-02-19T03:31:45.552Z · comments (12)
[link] Paper: Tell, Don't Show- Declarative facts influence how LLMs generalize
Owain_Evans · 2023-12-19T19:14:26.423Z · comments (4)
AI #53: One More Leap
Zvi · 2024-02-29T16:10:04.049Z · comments (0)
AI #36: In the Background
Zvi · 2023-11-02T18:00:01.803Z · comments (5)
[link] Towards Evaluating AI Systems for Moral Status Using Self-Reports
Ethan Perez (ethan-perez) · 2023-11-16T20:18:51.730Z · comments (3)
On Tapping Out
Screwtape · 2023-11-17T03:23:55.880Z · comments (13)
Apply to LASR Labs: a London-based technical AI safety research programme
Erin Robertson · 2024-04-09T17:34:06.847Z · comments (1)
[link] Open Sourcing Metaculus
ChristianWilliams · 2024-07-02T22:30:01.339Z · comments (0)
[link] Chinese scientists acknowledge xrisk & call for international regulatory body [Linkpost]
Akash (akash-wasil) · 2023-11-01T13:28:43.723Z · comments (4)
Laying the Foundations for Vision and Multimodal Mechanistic Interpretability & Open Problems
Sonia Joseph (redhat) · 2024-03-13T17:09:17.027Z · comments (13)
Higher-Order Forecasts
ozziegooen · 2024-05-22T21:49:42.802Z · comments (1)
Userscript to always show LW comments in context vs at the top
Vlad Sitalo (harcisis) · 2023-11-21T17:53:30.418Z · comments (8)
On the Contrary, Steelmanning Is Normal; ITT-Passing Is Niche
Zack_M_Davis · 2024-01-09T23:12:20.349Z · comments (31)
When Does Altruism Strengthen Altruism?
jefftk (jkaufman) · 2024-01-21T18:50:05.424Z · comments (2)
AI #60: Oh the Humanity
Zvi · 2024-04-18T14:10:02.281Z · comments (7)
On Trust
johnswentworth · 2023-12-06T19:19:07.680Z · comments (26)
AI #38: Let’s Make a Deal
Zvi · 2023-11-16T19:50:05.442Z · comments (2)
Announcing Atlas Computing
miyazono · 2024-04-11T15:56:31.241Z · comments (4)
[link] Fluent dreaming for language models (AI interpretability method)
tbenthompson (ben-thompson) · 2024-02-06T06:02:59.296Z · comments (4)
[link] Level up your spreadsheeting
angelinahli · 2024-05-25T14:57:19.730Z · comments (11)
~80 Interesting Questions about Foundation Model Agent Safety
RohanS · 2024-10-28T16:37:04.713Z · comments (4)
Economics Roundup #3
Zvi · 2024-09-10T13:50:06.955Z · comments (9)
Start an Upper-Room UV Installation Company?
jefftk (jkaufman) · 2024-10-19T02:00:10.691Z · comments (9)
Case Study: Interpreting, Manipulating, and Controlling CLIP With Sparse Autoencoders
Gytis Daujotas (gytis-daujotas) · 2024-08-01T21:08:38.800Z · comments (6)
An Introduction to AI Sandbagging
Teun van der Weij (teun-van-der-weij) · 2024-04-26T13:40:00.126Z · comments (8)
[link] Against Student Debt Cancellation From All Sides of the Political Compass
Maxwell Tabarrok (maxwell-tabarrok) · 2024-05-13T14:55:57.525Z · comments (16)
D&D.Sci Long War: Defender of Data-mocracy
aphyer · 2024-04-26T22:30:15.780Z · comments (20)
[link] LLM Evaluators Recognize and Favor Their Own Generations
Arjun Panickssery (arjun-panickssery) · 2024-04-17T21:09:12.007Z · comments (1)
In defense of technological unemployment as the main AI concern
tailcalled · 2024-08-27T17:58:01.992Z · comments (36)
Simplifying Corrigibility – Subagent Corrigibility Is Not Anti-Natural
Rubi J. Hudson (Rubi) · 2024-07-16T22:44:17.128Z · comments (27)
Auditing failures vs concentrated failures
ryan_greenblatt · 2023-12-11T02:47:35.703Z · comments (0)
What does davidad want from «boundaries»?
Chipmonk · 2024-02-06T17:45:42.348Z · comments (1)
[question] "Deception Genre" What Books are like Project Lawful?
Double · 2024-08-28T17:19:52.172Z · answers+comments (20)
Back to Basics: Truth is Unitary
lsusr · 2024-03-29T21:10:33.399Z · comments (13)
ProLU: A Nonlinearity for Sparse Autoencoders
Glen Taggart · 2024-04-23T14:09:21.592Z · comments (4)
D&D.Sci Long War: Defender of Data-mocracy Evaluation & Ruleset
aphyer · 2024-05-14T03:35:10.586Z · comments (3)
Why does generalization work?
Martín Soto (martinsq) · 2024-02-20T17:51:10.424Z · comments (16)
[link] How bad is chlorinated water?
bhauth · 2023-12-13T18:00:12.640Z · comments (18)
← previous page (newer posts) · next page (older posts) →