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] [Paper] Stress-testing capability elicitation with password-locked models
Fabien Roger (Fabien) · 2024-06-04T14:52:50.204Z · comments (10)
Some for-profit AI alignment org ideas
Eric Ho (eh42) · 2023-12-14T14:23:20.654Z · comments (19)
[link] "AI Safety for Fleshy Humans" an AI Safety explainer by Nicky Case
habryka (habryka4) · 2024-05-03T18:10:12.478Z · comments (10)
Self-prediction acts as an emergent regularizer
Cameron Berg (cameron-berg) · 2024-10-23T22:27:03.664Z · comments (4)
[link] [Paper] AI Sandbagging: Language Models can Strategically Underperform on Evaluations
Teun van der Weij (teun-van-der-weij) · 2024-06-13T10:04:49.556Z · comments (10)
Newsom Vetoes SB 1047
Zvi · 2024-10-01T12:20:06.127Z · comments (6)
MATS Winter 2023-24 Retrospective
utilistrutil · 2024-05-11T00:09:17.059Z · comments (28)
Sparse Autoencoders Work on Attention Layer Outputs
Connor Kissane (ckkissane) · 2024-01-16T00:26:14.767Z · comments (9)
Why you should be using a retinoid
GeneSmith · 2024-08-19T03:07:41.722Z · comments (57)
Retirement Accounts and Short Timelines
jefftk (jkaufman) · 2024-02-19T18:50:05.231Z · comments (35)
OpenAI o1, Llama 4, and AlphaZero of LLMs
Vladimir_Nesov · 2024-09-14T21:27:41.241Z · comments (24)
AI #51: Altman’s Ambition
Zvi · 2024-02-20T19:50:07.439Z · comments (5)
[link] What Depression Is Like
Sable · 2024-08-27T17:43:22.549Z · comments (23)
Actually, Power Plants May Be an AI Training Bottleneck.
Lao Mein (derpherpize) · 2024-06-20T04:41:33.567Z · comments (13)
An Introduction To The Mandelbrot Set That Doesn't Mention Complex Numbers
Yitz (yitz) · 2024-01-17T09:48:07.930Z · comments (11)
[link] Essay competition on the Automation of Wisdom and Philosophy — $25k in prizes
owencb · 2024-04-16T10:10:13.338Z · comments (12)
Agent Boundaries Aren't Markov Blankets. [Unless they're non-causal; see comments.]
abramdemski · 2023-11-20T18:23:40.443Z · comments (11)
Some Vacation Photos
johnswentworth · 2024-01-04T17:15:01.187Z · comments (0)
Release: Optimal Weave (P1): A Prototype Cohabitive Game
mako yass (MakoYass) · 2024-08-17T14:08:18.947Z · comments (21)
AI #83: The Mask Comes Off
Zvi · 2024-09-26T12:00:08.689Z · comments (19)
My Criticism of Singular Learning Theory
Joar Skalse (Logical_Lunatic) · 2023-11-19T15:19:16.874Z · comments (56)
Secular interpretations of core perennialist claims
zhukeepa · 2024-08-25T23:41:02.683Z · comments (32)
Decomposing the QK circuit with Bilinear Sparse Dictionary Learning
keith_wynroe · 2024-07-02T13:17:16.352Z · comments (7)
Values Are Real Like Harry Potter
johnswentworth · 2024-10-09T23:42:24.724Z · comments (17)
How to prevent collusion when using untrusted models to monitor each other
Buck · 2024-09-25T18:58:20.693Z · comments (5)
[link] Palworld development blog post
bhauth · 2024-01-28T05:56:19.984Z · comments (12)
AISafety.com – Resources for AI Safety
Søren Elverlin (soren-elverlin-1) · 2024-05-17T15:57:11.712Z · comments (3)
Constructability: Plainly-coded AGIs may be feasible in the near future
Épiphanie Gédéon (joy_void_joy) · 2024-04-27T16:04:45.894Z · comments (13)
Refusal mechanisms: initial experiments with Llama-2-7b-chat
Andy Arditi (andy-arditi) · 2023-12-08T17:08:01.250Z · comments (7)
[link] New voluntary commitments (AI Seoul Summit)
Zach Stein-Perlman · 2024-05-21T11:00:41.794Z · comments (17)
Studying The Alien Mind
Quentin FEUILLADE--MONTIXI (quentin-feuillade-montixi) · 2023-12-05T17:27:28.049Z · comments (10)
The Gemini Incident
Zvi · 2024-02-22T21:00:04.594Z · comments (19)
Survey of 2,778 AI authors: six parts in pictures
KatjaGrace · 2024-01-06T04:43:34.590Z · comments (1)
[link] Not every accommodation is a Curb Cut Effect: The Handicapped Parking Effect, the Clapper Effect, and more
Michael Cohn (michael-cohn) · 2024-09-15T05:27:36.691Z · comments (39)
Self-Referential Probabilistic Logic Admits the Payor's Lemma
Yudhister Kumar (randomwalks) · 2023-11-28T10:27:29.029Z · comments (14)
3C's: A Recipe For Mathing Concepts
johnswentworth · 2024-07-03T01:06:11.944Z · comments (5)
[link] My thesis (Algorithmic Bayesian Epistemology) explained in more depth
Eric Neyman (UnexpectedValues) · 2024-05-09T19:43:16.543Z · comments (4)
[link] MIRI's May 2024 Newsletter
Harlan · 2024-05-15T00:13:30.153Z · comments (1)
Quick look: applications of chaos theory
Elizabeth (pktechgirl) · 2024-08-18T15:00:07.853Z · comments (51)
LessWrong Community Weekend 2024, open for applications
UnplannedCauliflower · 2024-05-01T10:18:21.992Z · comments (2)
Thomas Kwa's research journal
Thomas Kwa (thomas-kwa) · 2023-11-23T05:11:08.907Z · comments (1)
[Intuitive self-models] 2. Conscious Awareness
Steven Byrnes (steve2152) · 2024-09-25T13:29:02.820Z · comments (48)
The case for a negative alignment tax
Cameron Berg (cameron-berg) · 2024-09-18T18:33:18.491Z · comments (20)
Graceful Degradation
Screwtape · 2024-11-05T23:57:53.362Z · comments (8)
[link] The Cognitive-Theoretic Model of the Universe: A Partial Summary and Review
jessicata (jessica.liu.taylor) · 2024-03-27T19:59:27.893Z · comments (36)
Scaffolding for "Noticing Metacognition"
Raemon · 2024-10-09T17:54:13.657Z · comments (4)
Corrigibility = Tool-ness?
johnswentworth · 2024-06-28T01:19:48.883Z · comments (8)
Spaciousness In Partner Dance: A Naturalism Demo
LoganStrohl (BrienneYudkowsky) · 2023-11-19T07:00:19.555Z · comments (5)
EU policymakers reach an agreement on the AI Act
tlevin (trevor) · 2023-12-15T06:02:44.668Z · comments (7)
[link] Is "superhuman" AI forecasting BS? Some experiments on the "539" bot from the Centre for AI Safety
titotal (lombertini) · 2024-09-18T13:07:40.754Z · comments (3)
← previous page (newer posts) · next page (older posts) →