LessWrong 2.0 Reader

View: New · Old · Top

← previous page (newer posts) · next page (older posts) →

New Bill AB 501 to Prevent OpenAI's Non-profit Conversion
Peter Windberger (vinertising-support) · 2025-03-25T00:41:07.617Z · comments (1)
[link] Does Robust Agency Require a Self?
leebriskCyrano · 2025-03-25T00:25:58.644Z · comments (0)
Takes on Takeoff
atharva · 2025-03-25T00:20:07.915Z · comments (0)
An overview of control measures
ryan_greenblatt · 2025-03-24T23:16:49.400Z · comments (0)
Populectomy.ai
YonatanK (jonathan-kallay) · 2025-03-24T22:06:24.680Z · comments (2)
Policy for LLM Writing on LessWrong
jimrandomh · 2025-03-24T21:41:30.965Z · comments (58)
Analyzing long agent transcripts (Docent)
jsteinhardt · 2025-03-24T20:49:54.472Z · comments (2)
Convergence 2024 Impact Review
David_Kristoffersson · 2025-03-24T20:28:58.422Z · comments (0)
The Best Lecture Series on Every Subject
Rauno Arike (rauno-arike) · 2025-03-24T20:03:14.772Z · comments (1)
[link] Recent AI model progress feels mostly like bullshit
lc · 2025-03-24T19:28:43.450Z · comments (75)
Learning about AI regulation should be easier
mfg (Magnus Gjerde) · 2025-03-24T19:22:33.824Z · comments (0)
Speaker For AIs Soul
Max Abecassis (max@customplay.com) · 2025-03-24T19:20:31.509Z · comments (0)
Advanced AI Systems Will Not Follow Historical Technological Patterns and Will Not Suffer the Misattribution of Productivity Gains
Max Abecassis (max@customplay.com) · 2025-03-24T19:20:31.486Z · comments (0)
AI "Deep Research" Tools Reviewed
sarahconstantin · 2025-03-24T18:40:03.864Z · comments (5)
Notes on countermeasures for exploration hacking (aka sandbagging)
ryan_greenblatt · 2025-03-24T18:39:36.665Z · comments (4)
Subversion Strategy Eval: Can language models statelessly strategize to subvert control protocols?
Alex Mallen (alex-mallen) · 2025-03-24T17:55:59.358Z · comments (0)
Straightforward Steps to Marginally Improve Odds of Whole Brain Emulation
Dom Polsinelli (dom-polsinelli) · 2025-03-24T17:14:38.794Z · comments (20)
From Loops to Klein Bottles: Uncovering Hidden Topology in High Dimensional Data
Gunnar Carlsson (gunnar-carlsson) · 2025-03-24T17:09:32.945Z · comments (0)
[link] Will Jesus Christ return in an election year?
Eric Neyman (UnexpectedValues) · 2025-03-24T16:50:53.019Z · comments (44)
[link] Sentinel's Global Risks Weekly Roundup #12/2025: Famine in Gaza, H7N9 outbreak, US geopolitical leadership weakening.
NunoSempere (Radamantis) · 2025-03-24T16:46:51.490Z · comments (0)
AI, Greed, and the Death of Oversight: When Institutions Ignore Their Own Limits
funnyfranco · 2025-03-24T15:03:16.802Z · comments (0)
[link] Delicious Boy Slop - Boring Diet, Effortless Weightloss
sapphire (deluks917) · 2025-03-24T15:01:58.355Z · comments (8)
Hong Kong ACX Spring Meetup 2025
fbreton · 2025-03-24T14:27:11.854Z · comments (0)
More on Various AI Action Plans
Zvi · 2025-03-24T13:10:05.637Z · comments (0)
Emergent scaling effects on the functional hierarchies within LLMs
Foop · 2025-03-24T13:03:30.930Z · comments (0)
Recommender Alignment for Lock-In Risk
alamerton · 2025-03-24T12:56:46.389Z · comments (0)
Edge Cases in AI Alignment
Florian_Dietz · 2025-03-24T09:27:58.164Z · comments (3)
Towards an understanding of the Chinese AI scene
Mitchell_Porter · 2025-03-24T09:10:19.498Z · comments (0)
Selective modularity: a research agenda
cloud · 2025-03-24T04:12:44.822Z · comments (2)
Pictures for 2024
jefftk (jkaufman) · 2025-03-24T02:40:07.051Z · comments (0)
Notes on handling non-concentrated failures with AI control: high level methods and different regimes
ryan_greenblatt · 2025-03-24T01:00:38.222Z · comments (3)
We need (a lot) more rogue agent honeypots
Ozyrus · 2025-03-23T22:24:52.785Z · comments (11)
What's the word for the amount of expertise that I, an experienced therapy patient and generally educated person, have on psychology topics?
danielechlin · 2025-03-23T17:38:28.881Z · comments (0)
Probability Theory Fundamentals 102: Source of the Sample Space
Ape in the coat · 2025-03-23T17:23:57.790Z · comments (17)
How to mitigate sandbagging
Teun van der Weij (teun-van-der-weij) · 2025-03-23T17:19:07.452Z · comments (0)
Tabula Bio: towards a future free of disease (& looking for collaborators)
mpoon (michael-poon) · 2025-03-23T16:30:15.523Z · comments (14)
Solving willpower seems easier than solving aging
Yair Halberstadt (yair-halberstadt) · 2025-03-23T15:25:40.861Z · comments (28)
[question] Should I fundraise for open source search engine?
samuelshadrach (xpostah) · 2025-03-23T13:04:16.149Z · answers+comments (0)
[link] Privateers Reborn: Cyber Letters of Marque
arealsociety (shane-zabel) · 2025-03-23T03:39:25.990Z · comments (2)
Beware nerfing AI with opinionated human-centric sensors
Haotian (haotian-huang) · 2025-03-23T01:09:16.770Z · comments (0)
Reframing AI Safety as a Neverending Institutional Challenge
scasper · 2025-03-23T00:13:48.614Z · comments (12)
The Dangerous Illusion of AI Deterrence: Why MAIM Isn’t Rational
mc1soft · 2025-03-22T22:55:02.355Z · comments (0)
Dayton, Ohio, ACX Meetup
Lunawarrior · 2025-03-22T19:45:55.510Z · comments (0)
[Replication] Crosscoder-based Stage-Wise Model Diffing
annas (annasoli) · 2025-03-22T18:35:19.003Z · comments (0)
The Principle of Satisfying Foreknowledge
Randall Reams (randall-reams) · 2025-03-22T18:20:27.998Z · comments (0)
[question] Urgency in the ITN framework
Shaïman · 2025-03-22T18:16:07.900Z · answers+comments (2)
Transhumanism and AI: Toward Prosperity or Extinction?
Shaïman · 2025-03-22T18:16:07.868Z · comments (2)
Tied Crosscoders: Explaining Chat Behavior from Base Model
Santiago Aranguri (aranguri) · 2025-03-22T18:07:21.751Z · comments (0)
Dusty Hands and Geo-arbitrage
Tomás B. (Bjartur Tómas) · 2025-03-22T16:05:30.364Z · comments (3)
100+ concrete projects and open problems in evals
Marius Hobbhahn (marius-hobbhahn) · 2025-03-22T15:21:40.970Z · comments (1)
← previous page (newer posts) · next page (older posts) →