LessWrong 2.0 Reader

View: New · Old · Top

next page (older posts) →

minifest
Austin Chen (austin-chen) · 2024-12-07T03:50:38.573Z · comments (1)
Mask and Respirator Intelligibility Comparison
jefftk (jkaufman) · 2024-12-07T03:20:01.585Z · comments (0)
Broadening Horizons: Rethinking Social Mobility Through Skill Diversification
Yanling Guo (yanling-guo) · 2024-12-07T00:04:20.046Z · comments (0)
Purging Corrupted Capabilities across Language Models
Amirali Abdullah (amirali-abdullah) · 2024-12-06T22:56:33.519Z · comments (0)
[link] Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
cloud · 2024-12-06T22:19:26.717Z · comments (0)
[link] Understanding Shapley Values with Venn Diagrams
agucova · 2024-12-06T21:56:43.960Z · comments (0)
Model Integrity
ryan.lowe · 2024-12-06T21:28:20.775Z · comments (0)
[link] Can AI improve the current state of molecular simulation?
Abhishaike Mahajan (abhishaike-mahajan) · 2024-12-06T20:22:31.685Z · comments (0)
Low Temperature Solomonoff Induction
dil-leik-og (samuel-buteau) · 2024-12-06T18:55:08.948Z · comments (0)
[link] Artificial Intelligence Against All Artificial Intelligence
kabusu (levi-zhaozhi) · 2024-12-06T16:31:18.324Z · comments (0)
Experiments are in the territory, results are in the map
Tahp · 2024-12-06T15:44:50.412Z · comments (1)
[link] A car journey with conservative evangelicals - Understanding some British political-religious beliefs
Nathan Young · 2024-12-06T11:22:45.563Z · comments (1)
Frontier Models are Capable of In-context Scheming
Marius Hobbhahn (marius-hobbhahn) · 2024-12-05T22:11:17.320Z · comments (11)
[link] Should you be worried about H5N1?
gw · 2024-12-05T21:11:06.996Z · comments (2)
[link] Are SAE features from the Base Model still meaningful to LLaVA?
Shan23Chen (shan-chen) · 2024-12-05T20:21:55.501Z · comments (0)
[link] o1 tried to avoid being shut down
Raelifin · 2024-12-05T19:52:03.620Z · comments (5)
More Growth, Melancholy, and MindCraft @3QD [revised and updated]
Bill Benzon (bill-benzon) · 2024-12-05T19:36:02.289Z · comments (0)
[link] Expevolu, a laissez-faire approach to country creation
Fernando · 2024-12-05T19:29:24.011Z · comments (2)
Are SAE features from the Base Model still meaningful to LLaVA?
Shan23Chen (shan-chen) · 2024-12-05T19:24:34.727Z · comments (0)
[link] OpenAI o1 + ChatGPT Pro release
anaguma · 2024-12-05T19:13:21.843Z · comments (0)
Smart people should do biology
Haotian Huang (haotian-huang) · 2024-12-05T19:11:20.671Z · comments (2)
[link] Announcement: AI for Math Fund
sarahconstantin · 2024-12-05T18:33:13.556Z · comments (2)
Detection of Asymptomatically Spreading Pathogens
jefftk (jkaufman) · 2024-12-05T18:20:02.473Z · comments (3)
[link] Model Integrity: MAI on Value Alignment
Jonas Hallgren · 2024-12-05T17:11:31.707Z · comments (9)
[link] Social Science in its epistemological context
Arturo Macias (arturo-macias) · 2024-12-05T16:12:29.034Z · comments (0)
[link] Why muscle tension can be unsexy
Chipmonk · 2024-12-05T16:11:39.212Z · comments (9)
What If We Rebuild Motivation with the Fermi ESTIMATion?
Gabriel Brito (gabriel-brito) · 2024-12-05T15:35:21.234Z · comments (0)
Higher and lower pleasures
Chris_Leong · 2024-12-05T13:13:46.526Z · comments (3)
[link] Sam Harris’s Argument For Objective Morality
Zero Contradictions · 2024-12-05T10:19:03.701Z · comments (4)
Morality as Cooperation Part III: Failure Modes
DeLesley Hutchins (delesley-hutchins) · 2024-12-05T09:39:27.816Z · comments (0)
Morality as Cooperation Part II: Theory and Experiment
DeLesley Hutchins (delesley-hutchins) · 2024-12-05T09:04:12.167Z · comments (0)
Morality as Cooperation Part I: Humans
DeLesley Hutchins (delesley-hutchins) · 2024-12-05T08:16:51.778Z · comments (0)
I Finally Worked Through Bayes' Theorem (Personal Achievement)
keltan · 2024-12-05T02:04:16.547Z · comments (6)
The Dream Machine
sarahconstantin · 2024-12-05T00:00:05.796Z · comments (5)
Should you have children? A decision framework for a crucial life choice that affects yourself, your child and the world
Sherrinford · 2024-12-04T23:14:23.950Z · comments (0)
CCing Mailing Lists on External Communication
jefftk (jkaufman) · 2024-12-04T22:00:02.038Z · comments (0)
[link] Picking favourites is hard
dkl9 · 2024-12-04T20:46:47.470Z · comments (3)
[question] How can I convince my cryptobro friend that S&P500 is efficient?
AhmedNeedsATherapist · 2024-12-04T20:04:44.521Z · answers+comments (9)
The 2023 LessWrong Review: The Basic Ask
Raemon · 2024-12-04T19:52:40.435Z · comments (19)
[link] Is the AI Doomsday Narrative the Product of a Big Tech Conspiracy?
garrison · 2024-12-04T19:20:59.286Z · comments (1)
[question] AI box question
KvmanThinking (avery-liu) · 2024-12-04T19:03:43.201Z · answers+comments (2)
[link] The Polite Coup
Charlie Sanders (charlie-sanders) · 2024-12-04T14:03:36.663Z · comments (0)
Analysis of Global AI Governance Strategies
Sammy Martin (SDM) · 2024-12-04T10:45:25.311Z · comments (7)
[question] Cryonics considerations: how big of a problem is ischemia?
kman · 2024-12-04T04:45:06.629Z · answers+comments (1)
AI #93: Happy Tuesday
Zvi · 2024-12-04T00:30:06.891Z · comments (1)
A Qualitative Case for LTFF: Filling Critical Ecosystem Gaps
Linch · 2024-12-03T21:57:23.597Z · comments (2)
Deep Causal Transcoding: A Framework for Mechanistically Eliciting Latent Behaviors in Language Models
Andrew Mack (andrew-mack) · 2024-12-03T21:19:42.333Z · comments (4)
"Alignment at Large": Bending the Arc of History Towards Life-Affirming Futures
welfvh · 2024-12-03T21:17:56.466Z · comments (0)
[link] Roots of Progress is hiring an event manager
jasoncrawford · 2024-12-03T20:46:42.929Z · comments (0)
Do simulacra dream of digital sheep?
EuanMcLean (euanmclean) · 2024-12-03T20:25:46.296Z · comments (33)
next page (older posts) →