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) →

Update #2 to "Dominant Assurance Contract Platform": EnsureDone
moyamo · 2023-11-28T18:02:50.367Z · comments (2)
Mech Interp Lacks Good Paradigms
Daniel Tan (dtch1997) · 2024-07-16T15:47:32.171Z · comments (0)
2024 ACX Predictions: Blind/Buy/Sell/Hold
Zvi · 2024-01-09T19:30:06.388Z · comments (2)
AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them
Roman Leventov · 2023-12-27T14:51:37.713Z · comments (9)
Musings on LLM Scale (Jul 2024)
Vladimir_Nesov · 2024-07-03T18:35:48.373Z · comments (0)
[link] On Lies and Liars
Gabriel Alfour (gabriel-alfour-1) · 2023-11-17T17:13:03.726Z · comments (4)
My disagreements with "AGI ruin: A List of Lethalities"
Noosphere89 (sharmake-farah) · 2024-09-15T17:22:18.367Z · comments (44)
What AI companies should do: Some rough ideas
Zach Stein-Perlman · 2024-10-21T14:00:10.412Z · comments (10)
Proveably Safe Self Driving Cars [Modulo Assumptions]
Davidmanheim · 2024-09-15T13:58:19.472Z · comments (26)
[link] Information dark matter
Logan Kieller (logan-kieller) · 2024-10-01T15:05:41.159Z · comments (4)
[question] Is AlphaGo actually a consequentialist utility maximizer?
faul_sname · 2023-12-07T12:41:05.132Z · answers+comments (8)
An illustrative model of backfire risks from pausing AI research
Maxime Riché (maxime-riche) · 2023-11-06T14:30:58.615Z · comments (3)
We have promising alignment plans with low taxes
Seth Herd · 2023-11-10T18:51:38.604Z · comments (9)
ChatGPT 4 solved all the gotcha problems I posed that tripped ChatGPT 3.5
VipulNaik · 2023-11-29T18:11:53.252Z · comments (16)
[question] Do websites and apps actually generally get worse after updates, or is it just an effect of the fear of change?
lillybaeum · 2023-12-10T17:26:34.206Z · answers+comments (34)
The Consciousness Box
GradualImprovement · 2023-12-11T16:45:08.172Z · comments (22)
Takeaways from a Mechanistic Interpretability project on “Forbidden Facts”
Tony Wang (tw) · 2023-12-15T11:05:23.256Z · comments (8)
Boston Solstice 2023 Retrospective
jefftk (jkaufman) · 2024-01-02T03:10:05.694Z · comments (0)
Introducing REBUS: A Robust Evaluation Benchmark of Understanding Symbols
Arjun Panickssery (arjun-panickssery) · 2024-01-15T21:21:03.962Z · comments (0)
[link] Vacuum: Theory and Technologies
ethanmorse · 2024-01-21T17:23:49.257Z · comments (0)
LLMs can strategically deceive while doing gain-of-function research
Igor Ivanov (igor-ivanov) · 2024-01-24T15:45:08.795Z · comments (4)
One True Love
Zvi · 2024-02-09T15:10:05.298Z · comments (7)
More on the Apple Vision Pro
Zvi · 2024-02-13T17:40:05.388Z · comments (5)
[link] FTX expects to return all customer money; clawbacks may go away
Mikhail Samin (mikhail-samin) · 2024-02-14T03:43:13.218Z · comments (1)
Sparse autoencoders find composed features in small toy models
Evan Anders (evan-anders) · 2024-03-14T18:00:43.339Z · comments (12)
Rational Animations offers animation production and writing services!
Writer · 2024-03-15T17:26:07.976Z · comments (0)
Experimentation (Part 7 of "The Sense Of Physical Necessity")
LoganStrohl (BrienneYudkowsky) · 2024-03-18T21:25:56.527Z · comments (0)
Monthly Roundup #16: March 2024
Zvi · 2024-03-19T13:10:05.529Z · comments (4)
Templates I made to run feedback rounds for Ethan Perez’s research fellows.
Henry Sleight (ResentHighly) · 2024-03-28T19:41:15.506Z · comments (0)
Effectively Handling Disagreements - Introducing a New Workshop
Camille Berger (Camille Berger) · 2024-04-15T16:33:50.339Z · comments (2)
UDT1.01: Logical Inductors and Implicit Beliefs (5/10)
Diffractor · 2024-04-18T08:39:13.368Z · comments (2)
AI #63: Introducing Alpha Fold 3
Zvi · 2024-05-09T14:20:03.176Z · comments (2)
"Which chains-of-thought was that faster than?"
Emrik (Emrik North) · 2024-05-22T08:21:00.269Z · comments (4)
One way violinists fail
Solenoid_Entity · 2024-05-29T04:08:17.675Z · comments (5)
Important open problems in voting
Closed Limelike Curves · 2024-07-01T02:53:44.690Z · comments (1)
How good are LLMs at doing ML on an unknown dataset?
Håvard Tveit Ihle (havard-tveit-ihle) · 2024-07-01T09:04:03.687Z · comments (4)
[link] patent process problems
bhauth · 2024-07-14T21:12:04.953Z · comments (13)
Confusing the metric for the meaning: Perhaps correlated attributes are "natural"
NickyP (Nicky) · 2024-07-23T12:43:18.681Z · comments (3)
Monthly Roundup #20: July 2024
Zvi · 2024-07-23T12:50:07.991Z · comments (9)
[link] The Cancer Resolution?
PeterMcCluskey · 2024-07-24T00:25:17.322Z · comments (24)
[link] AI Safety Memes Wiki
plex (ete) · 2024-07-24T18:53:04.977Z · comments (1)
[link] Twitter thread on open-source AI
Richard_Ngo (ricraz) · 2024-07-31T00:26:11.655Z · comments (6)
How I build and run behavioral interviews
benkuhn · 2024-02-26T05:50:05.328Z · comments (6)
Video and transcript of presentation on Scheming AIs
Joe Carlsmith (joekc) · 2024-03-22T15:52:03.311Z · comments (1)
Comparing Quantized Performance in Llama Models
NickyP (Nicky) · 2024-07-15T16:01:24.960Z · comments (2)
An Introduction to Representation Engineering - an activation-based paradigm for controlling LLMs
Jan Wehner · 2024-07-14T10:37:21.544Z · comments (4)
Learning Math in Time for Alignment
Nicholas / Heather Kross (NicholasKross) · 2024-01-09T01:02:37.446Z · comments (3)
In Defense of Lawyers Playing Their Part
Isaac King (KingSupernova) · 2024-07-01T01:32:58.695Z · comments (9)
[link] Manifund: 2023 in Review
Austin Chen (austin-chen) · 2024-01-18T23:50:13.557Z · comments (0)
[link] A computational complexity argument for many worlds
jessicata (jessica.liu.taylor) · 2024-08-13T19:35:10.116Z · comments (15)
← previous page (newer posts) · next page (older posts) →