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) →

Standard SAEs Might Be Incoherent: A Choosing Problem & A “Concise” Solution
Kola Ayonrinde (kola-ayonrinde) · 2024-10-30T22:50:45.642Z · comments (0)
[link] Altruism and Vitalism Aren't Fellow Travelers
Arjun Panickssery (arjun-panickssery) · 2024-08-09T02:01:11.361Z · comments (2)
[link] "25 Lessons from 25 Years of Marriage" by honorary rationalist Ferrett Steinmetz
CronoDAS · 2024-10-02T22:42:30.509Z · comments (2)
Apply to the Cooperative AI PhD Fellowship by October 14th!
Lewis Hammond (lewis-hammond-1) · 2024-10-05T12:41:24.093Z · comments (0)
[link] Foundations - Why Britain has stagnated [crosspost]
Nathan Young · 2024-09-23T10:43:20.411Z · comments (1)
Would you benefit from, or object to, a page with LW users' reacts?
Raemon · 2024-08-20T16:35:47.568Z · comments (6)
AI #77: A Few Upgrades
Zvi · 2024-08-20T00:20:09.717Z · comments (3)
[link] The Offense-Defense Balance of Gene Drives
Maxwell Tabarrok (maxwell-tabarrok) · 2024-09-27T16:47:25.976Z · comments (1)
[LDSL#2] Latent variable models, network models, and linear diffusion of sparse lognormals
tailcalled · 2024-08-09T19:57:56.122Z · comments (2)
[link] Tokyo AI Safety 2025: Call For Papers
Blaine (blaine-rogers) · 2024-10-21T08:43:38.467Z · comments (0)
[link] The unreasonable effectiveness of plasmid sequencing as a service
Abhishaike Mahajan (abhishaike-mahajan) · 2024-10-08T02:02:55.352Z · comments (0)
[question] Money Pump Arguments assume Memoryless Agents. Isn't this Unrealistic?
Dalcy (Darcy) · 2024-08-16T04:16:23.159Z · answers+comments (6)
AI Safety University Organizing: Early Takeaways from Thirteen Groups
agucova · 2024-10-02T15:14:00.137Z · comments (0)
GPT-3.5 judges can supervise GPT-4o debaters in capability asymmetric debates
Charlie George (charlie-george) · 2024-08-27T20:44:08.683Z · comments (7)
[link] A Defense of Peer Review
Niko_McCarty (niko-2) · 2024-10-22T16:16:49.982Z · comments (1)
Rashomon - A newsbetting site
ideasthete · 2024-10-15T18:15:02.476Z · comments (8)
Why the 2024 election matters, the AI risk case for Harris, & what you can do to help
Alex Lintz (alex-lintz) · 2024-09-24T19:32:46.893Z · comments (6)
A suite of Vision Sparse Autoencoders
Louka Ewington-Pitsos (louka-ewington-pitsos) · 2024-10-27T04:05:20.377Z · comments (0)
Deception and Jailbreak Sequence: 1. Iterative Refinement Stages of Deception in LLMs
Winnie Yang (winnie-yang) · 2024-08-22T07:32:07.600Z · comments (0)
[link] How to choose what to work on
jasoncrawford · 2024-09-18T20:39:12.316Z · comments (6)
Can We Predict Persuasiveness Better Than Anthropic?
Lennart Finke (l-f) · 2024-08-04T14:05:33.668Z · comments (5)
[LDSL#3] Information-orientation is in tension with magnitude-orientation
tailcalled · 2024-08-10T21:58:27.659Z · comments (2)
[link] Hyperpolation
Gunnar_Zarncke · 2024-09-15T21:37:00.002Z · comments (6)
Monthly Roundup #21: August 2024
Zvi · 2024-08-20T00:20:08.178Z · comments (6)
[link] on Science Beakers and DDT
bhauth · 2024-09-05T03:21:21.382Z · comments (13)
Launching Adjacent News
Lucas Kohorst (lucas-kohorst) · 2024-10-16T17:58:10.289Z · comments (0)
A path to human autonomy
Nathan Helm-Burger (nathan-helm-burger) · 2024-10-29T03:02:42.475Z · comments (11)
[link] The Tech Industry is the Biggest Blocker to Meaningful AI Safety Regulations
garrison · 2024-08-16T19:37:28.416Z · comments (1)
[link] Day Zero Antivirals for Future Pandemics
Niko_McCarty (niko-2) · 2024-08-26T15:18:33.858Z · comments (2)
[link] AI safety tax dynamics
owencb · 2024-10-23T12:18:32.243Z · comments (0)
Geoffrey Hinton on the Past, Present, and Future of AI
Stephen McAleese (stephen-mcaleese) · 2024-10-12T16:41:56.796Z · comments (5)
Brief analysis of OP Technical AI Safety Funding
22tom (thomas-barnes) · 2024-10-25T19:37:41.674Z · comments (2)
August 2024 Time Tracking
jefftk (jkaufman) · 2024-08-24T13:50:04.676Z · comments (0)
[LDSL#5] Comparison and magnitude/diminishment
tailcalled · 2024-08-12T18:47:20.546Z · comments (0)
[link] To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-09-19T16:13:55.835Z · comments (1)
AXRP Episode 37 - Jaime Sevilla on Forecasting AI
DanielFilan · 2024-10-04T21:00:03.077Z · comments (3)
[question] What should OpenAI do that it hasn't already done, to stop their vacancies from being advertised on the 80k Job Board?
WitheringWeights (EZ97) · 2024-10-21T13:57:30.934Z · answers+comments (0)
Alignment by default: the simulation hypothesis
gb (ghb) · 2024-09-25T16:26:00.552Z · comments (39)
AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization
DanielFilan · 2024-08-24T22:30:02.039Z · comments (0)
[link] AI & wisdom 1: wisdom, amortised optimisation, and AI
L Rudolf L (LRudL) · 2024-10-28T21:02:51.215Z · comments (0)
[link] Anthropic is being sued for copying books to train Claude
Remmelt (remmelt-ellen) · 2024-08-31T02:57:27.092Z · comments (4)
Musings on Text Data Wall (Oct 2024)
Vladimir_Nesov · 2024-10-05T19:00:21.286Z · comments (2)
Gell-Mann checks
Cleo Scrolls (cleo-scrolls) · 2024-09-26T22:45:43.569Z · comments (7)
[question] What should we do about COVID in 2024?
ChristianKl · 2024-08-04T10:57:24.140Z · answers+comments (2)
[link] The Great Organism Theory of Evolution
rogersbacon · 2024-08-10T12:26:02.434Z · comments (0)
[link] Compression Moves for Prediction
adamShimi · 2024-09-14T17:51:12.004Z · comments (0)
[link] AI Model Registries: A Foundational Tool for AI Governance
Elliot Mckernon (elliot) · 2024-10-07T19:27:43.466Z · comments (1)
How Often Does Taking Away Options Help?
niplav · 2024-09-21T21:52:40.822Z · comments (6)
A necessary Membrane formalism feature
ThomasCederborg · 2024-09-10T21:33:09.508Z · comments (6)
[link] Green and golden: a meditation
Richard_Ngo (ricraz) · 2024-08-18T01:36:43.613Z · comments (0)
← previous page (newer posts) · next page (older posts) →