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) →

Gwerns
Tomás B. (Bjartur Tómas) · 2024-11-16T14:31:57.791Z · comments (2)
Filled Cupcakes
jefftk (jkaufman) · 2024-11-26T03:20:08.504Z · comments (2)
How Often Does Taking Away Options Help?
niplav · 2024-09-21T21:52:40.822Z · comments (6)
Text Posts from the Kids Group: 2018
jefftk (jkaufman) · 2024-11-23T12:50:05.325Z · comments (0)
Lab governance reading list
Zach Stein-Perlman · 2024-10-25T18:00:28.346Z · comments (3)
[link] AI Model Registries: A Foundational Tool for AI Governance
Elliot Mckernon (elliot) · 2024-10-07T19:27:43.466Z · comments (1)
Musings on Text Data Wall (Oct 2024)
Vladimir_Nesov · 2024-10-05T19:00:21.286Z · comments (2)
AI Can be “Gradient Aware” Without Doing Gradient hacking.
Sodium · 2024-10-20T21:02:10.754Z · comments (0)
A necessary Membrane formalism feature
ThomasCederborg · 2024-09-10T21:33:09.508Z · comments (6)
[link] Does natural selection favor AIs over humans?
cdkg · 2024-10-03T18:47:43.517Z · comments (1)
[link] Towards the Operationalization of Philosophy & Wisdom
Thane Ruthenis · 2024-10-28T19:45:07.571Z · comments (2)
Simon DeDeo on Explore vs Exploit in Science
Elizabeth (pktechgirl) · 2024-09-10T03:40:08.311Z · comments (0)
[question] What is the alpha in one bit of evidence?
J Bostock (Jemist) · 2024-10-22T21:57:09.056Z · answers+comments (13)
[question] Programmers, How Bad Is It out There?
Tomás B. (Bjartur Tómas) · 2024-11-20T00:57:16.802Z · answers+comments (4)
[link] Anthropic is being sued for copying books to train Claude
Remmelt (remmelt-ellen) · 2024-08-31T02:57:27.092Z · comments (4)
Gell-Mann checks
Cleo Scrolls (cleo-scrolls) · 2024-09-26T22:45:43.569Z · comments (7)
My decomposition of the alignment problem
Daniel C (harper-owen) · 2024-09-02T00:21:08.359Z · comments (22)
[link] Compression Moves for Prediction
adamShimi · 2024-09-14T17:51:12.004Z · comments (0)
[link] Mechanistic Interpretability of Llama 3.2 with Sparse Autoencoders
PaulPauls · 2024-11-24T05:45:20.124Z · comments (2)
Economics Roundup #4
Zvi · 2024-10-15T13:20:06.923Z · comments (4)
[link] Update on the Mysterious Trump Buyers on Polymarket
Annapurna (jorge-velez) · 2024-11-04T19:22:06.540Z · comments (9)
Why I'm bearish on mechanistic interpretability: the shards are not in the network
tailcalled · 2024-09-13T17:09:25.407Z · comments (40)
Review: “The Case Against Reality”
David Gross (David_Gross) · 2024-10-29T13:13:29.643Z · comments (9)
Why Reflective Stability is Important
Johannes C. Mayer (johannes-c-mayer) · 2024-09-05T15:28:19.913Z · comments (2)
Announcing the PIBBSS Symposium '24!
DusanDNesic · 2024-09-03T11:19:47.568Z · comments (0)
Bridging the VLM and mech interp communities for multimodal interpretability
Sonia Joseph (redhat) · 2024-10-28T14:41:41.969Z · comments (5)
[link] Chess As The Model Game
criticalpoints · 2024-11-17T19:45:26.499Z · comments (0)
[link] To Be Born in a Bag
Niko_McCarty (niko-2) · 2024-10-06T17:21:00.605Z · comments (1)
How likely is brain preservation to work?
Andy_McKenzie · 2024-11-18T16:58:54.632Z · comments (3)
[link] Fragile, Robust, and Antifragile Preference Satisfaction
adamShimi · 2024-11-02T17:25:55.986Z · comments (0)
Long Live the Usurper
pleiotroth · 2024-11-27T12:10:51.025Z · comments (0)
D/acc AI Security Salon
Allison Duettmann (allison-duettmann) · 2024-10-19T22:17:57.067Z · comments (0)
In the Name of All That Needs Saving
pleiotroth · 2024-11-07T15:26:12.252Z · comments (2)
"Real AGI"
Seth Herd · 2024-09-13T14:13:24.124Z · comments (20)
Announcing the CLR Foundations Course and CLR S-Risk Seminars
JamesFaville (elephantiskon) · 2024-11-19T01:18:10.085Z · comments (0)
[link] Should Sports Betting Be Banned?
Maxwell Tabarrok (maxwell-tabarrok) · 2024-09-21T14:13:35.404Z · comments (2)
Advisors for Smaller Major Donors?
jefftk (jkaufman) · 2024-11-06T14:30:06.187Z · comments (2)
Word Spaghetti
Gordon Seidoh Worley (gworley) · 2024-10-23T05:39:20.105Z · comments (9)
[link] AI & Liability Ideathon
Kabir Kumar (kabir-kumar) · 2024-11-26T13:54:01.820Z · comments (2)
Avoiding the Bog of Moral Hazard for AI
Nathan Helm-Burger (nathan-helm-burger) · 2024-09-13T21:24:34.137Z · comments (13)
[link] Instruction Following without Instruction Tuning
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-09-24T13:49:09.078Z · comments (0)
OpenAI defected, but we can take honest actions
Remmelt (remmelt-ellen) · 2024-10-21T08:41:25.728Z · comments (16)
[link] some questionable space launch guns
bhauth · 2024-10-13T22:52:26.418Z · comments (0)
Heresies in the Shadow of the Sequences
Cole Wyeth (Amyr) · 2024-11-14T05:01:11.889Z · comments (12)
My career exploration: Tools for building confidence
lynettebye · 2024-09-13T11:37:55.843Z · comments (0)
Using Dangerous AI, But Safely?
habryka (habryka4) · 2024-11-16T04:29:20.914Z · comments (2)
[link] Why Swiss watches and Taylor Swift are AGI-proof
Kevin Kohler (KevinKohler) · 2024-09-05T13:23:27.033Z · comments (11)
Proposal to increase fertility: University parent clubs
Fluffnutt (Pear) · 2024-11-18T04:21:26.346Z · comments (3)
Is Text Watermarking a lost cause?
egor.timatkov · 2024-10-01T16:20:51.113Z · comments (13)
Automating LLM Auditing with Developmental Interpretability
htlou · 2024-09-04T15:50:04.337Z · comments (0)
← previous page (newer posts) · next page (older posts) →