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] AI Safety at the Frontier: Paper Highlights, September '24
gasteigerjo · 2024-10-02T09:49:00.357Z · comments (0)
Something Is Lost When AI Makes Art
utilistrutil · 2024-08-18T22:53:46.951Z · comments (0)
[link] What are matching markets?
ohmurphy · 2024-07-27T15:05:28.647Z · comments (0)
[question] What are the actual arguments in favor of computationalism as a theory of identity?
sunwillrise (andrei-alexandru-parfeni) · 2024-07-18T18:44:20.751Z · answers+comments (24)
Source Control for Prototyping and Analysis
jefftk (jkaufman) · 2024-09-26T01:50:04.145Z · comments (0)
Binary encoding as a simple explicit construction for superposition
tailcalled · 2024-10-12T21:18:31.731Z · comments (0)
[Cross-post] Book Review: Bureaucracy, by James Q Wilson
davekasten · 2024-08-19T13:57:10.872Z · comments (0)
[link] The Golden Mean of Scientific Virtues
adamShimi · 2024-07-08T17:16:21.676Z · comments (4)
No Electricity in Manchuria
winstonBosan · 2024-11-19T01:11:58.661Z · comments (0)
[link] How to Fake Decryption
ohmurphy · 2024-09-05T09:18:41.586Z · comments (0)
Goal: Understand Intelligence
Johannes C. Mayer (johannes-c-mayer) · 2024-11-03T21:20:02.900Z · comments (19)
[question] What is AI Safety’s line of retreat?
Remmelt (remmelt-ellen) · 2024-07-28T05:43:05.021Z · answers+comments (12)
[question] If AI is in a bubble and the bubble bursts, what would you do?
Remmelt (remmelt-ellen) · 2024-08-19T10:56:03.948Z · answers+comments (13)
[link] How to wash your hands precisely and thoroughly
dkl9 · 2024-07-16T18:29:03.627Z · comments (0)
[link] Francois Chollet inadvertently limits his claim on ARC-AGI
Noosphere89 (sharmake-farah) · 2024-07-16T17:32:00.219Z · comments (3)
LLM Psychometrics and Prompt-Induced Psychopathy
Korbinian K. (korbinian-koch) · 2024-10-18T18:11:24.256Z · comments (2)
How I'd like alignment to get done (as of 2024-10-18)
TristanTrim · 2024-10-18T23:39:03.107Z · comments (2)
[link] AI Prejudices: Practical Implications
PeterMcCluskey · 2024-10-19T02:19:58.695Z · comments (0)
AXRP Episode 38.1 - Alan Chan on Agent Infrastructure
DanielFilan · 2024-11-16T23:30:09.098Z · comments (0)
The current state of RSPs
Zach Stein-Perlman · 2024-11-04T16:00:42.630Z · comments (0)
Clarifying Alignment Fundamentals Through the Lens of Ontology
eternal/ephemera · 2024-10-07T20:57:33.238Z · comments (4)
Lenses of Control
WillPetillo · 2024-10-22T07:51:06.355Z · comments (0)
2/3 Aussie & NZ AI Safety folk often or sometimes feel lonely or disconnected (and 16 other barriers to impact)
yanni kyriacos (yanni) · 2024-08-01T01:15:02.620Z · comments (0)
How I Wrought a Lesser Scribing Artifact (You Can, Too!)
Lorxus · 2024-08-02T03:35:00.972Z · comments (0)
Critique of 'Many People Fear A.I. They Shouldn't' by David Brooks.
Axel Ahlqvist (axelahlqvist1995@gmail.com) · 2024-08-15T18:38:13.437Z · comments (8)
Child Handrail Returns
jefftk (jkaufman) · 2024-07-14T12:40:04.988Z · comments (0)
GPT-4o Can In Some Cases Solve Moderately Complicated Captchas
dirk (abandon) · 2024-11-09T04:04:37.782Z · comments (2)
Do you want to do a debate on youtube? I'm looking for polite, truth-seeking participants.
Nathan Young · 2024-10-10T09:32:59.162Z · comments (0)
A Case for Conscious Significance rather than Free Will.
James Stephen Brown (james-brown) · 2024-10-25T23:20:30.834Z · comments (2)
Shutting down all competing AI projects might not buy a lot of time due to Internal Time Pressure
ThomasCederborg · 2024-10-03T00:01:34.011Z · comments (7)
Contextual Constitutional AI
aksh-n · 2024-09-28T23:24:43.529Z · comments (2)
SYSTEMA ROBOTICA
Ali Ahmed (roboticali) · 2024-08-12T20:34:45.879Z · comments (2)
Amoeba roles in tech
Sindhu Shivaprasad (sindhu-shivaprasad) · 2024-10-04T17:25:46.568Z · comments (0)
ML4Good (AI Safety Bootcamp) - Experience report
JanEbbing · 2024-11-05T01:18:43.554Z · comments (0)
Apartment Price Map Discontinuity
jefftk (jkaufman) · 2024-08-19T15:30:05.386Z · comments (0)
ML4Good Summer Bootcamps - Applications Open [deadline extended]
YM (Yannick_Muehlhaeuser_duplicate0.05902100825326273) · 2024-07-05T13:59:20.518Z · comments (0)
Editing at the Take Level
jefftk (jkaufman) · 2024-09-24T11:30:04.914Z · comments (1)
A Poem Is All You Need: Jailbreaking ChatGPT, Meta & More
Sharat Jacob Jacob (sharat-jacob-jacob) · 2024-10-29T12:41:30.337Z · comments (0)
Can startups be impactful in AI safety?
Esben Kran (esben-kran) · 2024-09-13T19:00:33.306Z · comments (0)
Why We Wouldn't Build Aligned AI Even If We Could
Snowyiu · 2024-11-16T20:19:59.324Z · comments (5)
[unlisted] Beneficial applications for current-level AI in human information systems? More likely than you'd think!
mako yass (MakoYass) · 2024-08-16T20:49:57.582Z · comments (0)
[link] [Linkpost] Building Altruistic and Moral AI Agent with Brain-inspired Affective Empathy Mechanisms
Gunnar_Zarncke · 2024-11-04T10:15:35.550Z · comments (0)
[link] The Computational Complexity of Circuit Discovery for Inner Interpretability
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-10-17T13:18:46.378Z · comments (2)
Conversational Signposts—An Antidote to Dull Social Interactions
Declan Molony (declan-molony) · 2024-10-22T05:37:56.175Z · comments (6)
Restructuring Pop Songs for Contra
jefftk (jkaufman) · 2024-08-18T14:10:04.029Z · comments (0)
Beyond Defensive Technology
ejk64 · 2024-10-14T11:34:24.595Z · comments (1)
[link] AISafety.info: What are Inductive Biases?
Algon · 2024-09-19T17:26:24.581Z · comments (4)
[link] Mechanistic Anomaly Detection Research Update
Nora Belrose (nora-belrose) · 2024-08-06T10:33:26.031Z · comments (0)
[link] Comparing Forecasting Track Records for AI Benchmarking and Beyond
ChristianWilliams · 2024-09-25T21:01:15.975Z · comments (0)
Switching to a Yamaha P-121 Keyboard
jefftk (jkaufman) · 2024-10-02T02:20:02.284Z · comments (0)
← previous page (newer posts) · next page (older posts) →