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) →

Scaling of AI training runs will slow down after GPT-5
Maxime Riché (maxime-riche) · 2024-04-26T16:05:59.957Z · comments (5)
[link] Progress Conference 2024: Toward Abundant Futures
jasoncrawford · 2024-06-26T15:39:45.267Z · comments (2)
Movie posters
KatjaGrace · 2024-03-06T06:20:03.034Z · comments (0)
instruction tuning and autoregressive distribution shift
nostalgebraist · 2024-09-05T16:53:41.497Z · comments (5)
[link] The Data Wall is Important
JustisMills · 2024-06-09T22:54:20.070Z · comments (20)
[link] "What if we could redesign society from scratch? The promise of charter cities." [Rational Animations video]
Jackson Wagner · 2024-02-18T00:57:50.444Z · comments (7)
[link] Forecasting: the way I think about it
Molly (hickman-santini) · 2024-05-09T00:49:01.768Z · comments (4)
List your AI X-Risk cruxes!
Aryeh Englander (alenglander) · 2024-04-28T18:26:19.327Z · comments (7)
[link] Book review: Cuisine and Empire
eukaryote · 2024-01-21T06:15:12.969Z · comments (2)
Planning to build a cryptographic box with perfect secrecy
Lysandre Terrisse · 2023-12-31T09:31:47.941Z · comments (6)
Applying Force to the Wrong End of a Causal Chain
silentbob · 2024-06-22T18:06:32.364Z · comments (0)
Long-Term Future Fund: May 2023 to March 2024 Payout recommendations
Linch · 2024-06-12T13:46:29.535Z · comments (0)
Ronny and Nate discuss what sorts of minds humanity is likely to find by Machine Learning
So8res · 2023-12-19T23:39:59.689Z · comments (30)
Californians, tell your reps to vote yes on SB 1047!
Holly_Elmore · 2024-08-12T19:50:09.817Z · comments (24)
Whiteboard Pen Magazines are Useful
Johannes C. Mayer (johannes-c-mayer) · 2024-07-12T17:15:33.200Z · comments (8)
D&D.Sci(-fi): Colonizing the SuperHyperSphere [Evaluation and Ruleset]
abstractapplic · 2024-01-22T19:20:05.001Z · comments (7)
Neuroscience and Alignment
Garrett Baker (D0TheMath) · 2024-03-18T21:09:52.004Z · comments (25)
Why did ChatGPT say that? Prompt engineering and more, with PIZZA.
Jessica Rumbelow (jessica-cooper) · 2024-08-03T12:07:46.302Z · comments (2)
[link] AI Regulation is Unsafe
Maxwell Tabarrok (maxwell-tabarrok) · 2024-04-22T16:37:55.431Z · comments (41)
"Does your paradigm beget new, good, paradigms?"
Raemon · 2024-01-25T18:23:15.497Z · comments (6)
Manifund Q1 Retro: Learnings from impact certs
Austin Chen (austin-chen) · 2024-05-01T16:48:33.140Z · comments (1)
The Serendipity of Density
jefftk (jkaufman) · 2023-12-17T03:50:04.824Z · comments (4)
[Linkpost] Play with SAEs on Llama 3
Tom McGrath · 2024-09-25T22:35:44.824Z · comments (2)
Monthly Roundup #23: October 2024
Zvi · 2024-10-16T13:50:05.869Z · comments (13)
Nitric oxide for covid and other viral infections
Elizabeth (pktechgirl) · 2024-02-07T21:30:03.774Z · comments (6)
You're a Space Wizard, Luke
lsusr · 2024-08-18T05:35:39.238Z · comments (6)
Apply to the PIBBSS Summer Research Fellowship
Nora_Ammann · 2024-01-12T04:06:58.328Z · comments (1)
Forget Everything (Statistical Mechanics Part 1)
J Bostock (Jemist) · 2024-04-22T13:33:35.446Z · comments (6)
[link] Legalize butanol?
bhauth · 2023-12-20T14:24:33.849Z · comments (20)
Logical Line-Of-Sight Makes Games Sequential or Loopy
StrivingForLegibility · 2024-01-19T04:05:44.782Z · comments (0)
Medical Roundup #3
Zvi · 2024-07-09T13:10:06.862Z · comments (4)
Simple distribution approximation: When sampled 100 times, can language models yield 80% A and 20% B?
Teun van der Weij (teun-van-der-weij) · 2024-01-29T00:24:27.706Z · comments (5)
Individually incentivized safe Pareto improvements in open-source bargaining
Nicolas Macé (NicolasMace) · 2024-07-17T18:26:43.619Z · comments (2)
Natural abstractions are observer-dependent: a conversation with John Wentworth
Martín Soto (martinsq) · 2024-02-12T17:28:38.889Z · comments (13)
[Interim research report] Evaluating the Goal-Directedness of Language Models
Rauno Arike (rauno-arike) · 2024-07-18T18:19:04.260Z · comments (4)
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
Kola Ayonrinde (kola-ayonrinde) · 2024-08-23T18:52:31.019Z · comments (5)
Prepsgiving, A Convergently Instrumental Human Practice
JenniferRM · 2023-11-23T17:24:56.784Z · comments (0)
Instrumental deception and manipulation in LLMs - a case study
Olli Järviniemi (jarviniemi) · 2024-02-24T02:07:01.769Z · comments (13)
[link] Understanding Gödel’s completeness theorem
jessicata (jessica.liu.taylor) · 2024-05-27T18:55:02.079Z · comments (0)
[link] [Paper] Language Models Don't Learn the Physical Manifestation of Language
Bruce W. Lee (bruce-lee) · 2024-02-22T18:52:32.237Z · comments (23)
[link] Linear infra-Bayesian Bandits
Vanessa Kosoy (vanessa-kosoy) · 2024-05-10T06:41:09.206Z · comments (5)
Stitching SAEs of different sizes
Bart Bussmann (Stuckwork) · 2024-07-13T17:19:20.506Z · comments (12)
I’m confused about innate smell neuroanatomy
Steven Byrnes (steve2152) · 2023-11-28T20:49:13.042Z · comments (2)
Anthropic rewrote its RSP
Zach Stein-Perlman · 2024-10-15T14:25:12.518Z · comments (19)
Signaling with Small Orange Diamonds
jefftk (jkaufman) · 2024-11-07T20:20:08.026Z · comments (1)
[link] FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI
Tamay · 2024-11-14T06:13:22.042Z · comments (0)
AI Safety Camp 10
Robert Kralisch (nonmali-1) · 2024-10-26T11:08:09.887Z · comments (9)
[link] An X-Ray is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation
hugofry · 2024-10-07T08:53:14.658Z · comments (0)
Compelling Villains and Coherent Values
Cole Wyeth (Amyr) · 2024-10-06T19:53:47.891Z · comments (4)
Open Source Replication of Anthropic’s Crosscoder paper for model-diffing
Connor Kissane (ckkissane) · 2024-10-27T18:46:21.316Z · comments (1)
← previous page (newer posts) · next page (older posts) →