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) →

Training a Sparse Autoencoder in < 30 minutes on 16GB of VRAM using an S3 cache
Louka Ewington-Pitsos (louka-ewington-pitsos) · 2024-08-24T07:39:00.057Z · comments (0)
[question] Is there any rigorous work on using anthropic uncertainty to prevent situational awareness / deception?
David Scott Krueger (formerly: capybaralet) (capybaralet) · 2024-09-04T12:40:07.678Z · answers+comments (7)
Thinking in 2D
sarahconstantin · 2024-10-20T19:30:05.842Z · comments (0)
[link] CultFrisbee
Gauraventh (aryangauravyadav) · 2024-08-11T21:36:36.550Z · comments (3)
Bridging the VLM and mech interp communities for multimodal interpretability
Sonia Joseph (redhat) · 2024-10-28T14:41:41.969Z · comments (5)
All the Following are Distinct
Gianluca Calcagni (gianluca-calcagni) · 2024-08-02T16:35:51.815Z · comments (3)
Hiring a writer to co-author with me (Spencer Greenberg for ClearerThinking.org)
spencerg · 2024-10-27T17:34:50.479Z · comments (0)
[question] Is there a CFAR handbook audio option?
FinalFormal2 · 2024-10-26T17:08:36.480Z · answers+comments (0)
The slingshot helps with learning
Wilson Wu (wilson-wu) · 2024-10-31T23:18:16.762Z · comments (0)
[link] Non-Transactional Compliments
Jonathan Moregård (JonathanMoregard) · 2024-08-09T13:42:16.471Z · comments (0)
The Residual Expansion: A Framework for thinking about Transformer Circuits
Daniel Tan (dtch1997) · 2024-08-02T11:04:56.347Z · comments (13)
[link] Why good things often don’t lead to better outcomes
DMMF · 2024-09-19T16:37:07.778Z · comments (1)
Slave Morality: A place for every man and every man in his place
Martin Sustrik (sustrik) · 2024-09-19T04:20:04.491Z · comments (7)
Review: Dr Stone
ProgramCrafter (programcrafter) · 2024-09-29T10:35:53.175Z · comments (5)
An information-theoretic study of lying in LLMs
Annah (annah) · 2024-08-02T10:06:39.312Z · comments (0)
Physical Therapy Sucks (but have you tried hiding it in some peanut butter?)
Declan Molony (declan-molony) · 2024-09-10T05:54:47.000Z · comments (12)
Appealing to the Public
jefftk (jkaufman) · 2024-10-23T19:00:07.669Z · comments (0)
[link] My lukewarm take on GLP-1 agonists
George3d6 · 2024-08-26T12:34:27.929Z · comments (0)
Interview with Robert Kralisch on Simulators
WillPetillo · 2024-08-26T05:49:15.543Z · comments (0)
Reducing global AI competition through the Commerce Control List and Immigration reform: a dual-pronged approach
Ben Smith (ben-smith) · 2024-09-03T05:28:24.549Z · comments (2)
Join a LessWrong Team for the Unaging System Challenge
Crissman · 2024-10-23T06:01:08.018Z · comments (4)
Simulation-aware causal decision theory: A case for one-boxing in CDT
kongus_bongus · 2024-08-09T18:09:20.013Z · comments (11)
Trading Candy
jefftk (jkaufman) · 2024-11-01T01:10:08.024Z · comments (1)
Automating LLM Auditing with Developmental Interpretability
htlou · 2024-09-04T15:50:04.337Z · comments (0)
Announcing the Ultimate Jailbreaking Championship
InnerHufflepuff (grayswan) · 2024-09-04T00:35:31.234Z · comments (1)
[link] Pronouns are Annoying
ymeskhout · 2024-09-18T13:30:04.620Z · comments (21)
[link] Verification methods for international AI agreements
Akash (akash-wasil) · 2024-08-31T14:58:10.986Z · comments (1)
Are LLMs on the Path to AGI?
Davidmanheim · 2024-08-30T03:14:04.710Z · comments (2)
[question] Any Trump Supporters Want to Dialogue?
k64 · 2024-09-28T19:41:55.370Z · answers+comments (80)
[link] Where is the Learn Everything System?
Shoshannah Tekofsky (DarkSym) · 2024-09-27T21:30:16.379Z · comments (8)
The deepest atheist: Sam Altman
Trey Edwin (Paolo Vivaldi) · 2024-10-10T03:27:34.465Z · comments (2)
Emergence, The Blind Spot of GenAI Interpretability?
Quentin FEUILLADE--MONTIXI (quentin-feuillade-montixi) · 2024-08-10T10:07:53.654Z · comments (7)
My hopes for YouCongress.com
Nathan Helm-Burger (nathan-helm-burger) · 2024-09-22T03:20:20.939Z · comments (3)
Humans are (mostly) metarational
Yair Halberstadt (yair-halberstadt) · 2024-10-09T05:51:16.644Z · comments (6)
[link] Runner's High On Demand: A Story of Luck & Persistence
Shoshannah Tekofsky (DarkSym) · 2024-09-29T17:15:29.494Z · comments (6)
[link] Benefits of Psyllium Dietary Fiber in Particular
Brendan Long (korin43) · 2024-08-28T18:13:23.891Z · comments (7)
Primary Perceptive Systems
ChristianKl · 2024-08-15T11:26:01.667Z · comments (2)
Funding for work that builds capacity to address risks from transformative AI
abergal · 2024-08-14T23:52:09.922Z · comments (0)
[link] AI x Human Flourishing: Introducing the Cosmos Institute
Brendan McCord (brendan-mccord) · 2024-09-05T18:23:32.690Z · comments (5)
Inverse Problems In Everyday Life
silentbob · 2024-10-15T11:42:30.276Z · comments (1)
[link] The Ap Distribution
criticalpoints · 2024-08-24T21:45:35.029Z · comments (3)
Pomodoro Method Randomized Self Experiment
niplav · 2024-09-29T21:55:04.740Z · comments (2)
[question] Looking to interview AI Safety researchers for a book
jeffreycaruso · 2024-08-24T19:57:33.119Z · answers+comments (0)
Against Explosive Growth
c.trout (ctrout) · 2024-09-04T21:45:03.120Z · comments (1)
[question] What are your favorite books or blogs that are out of print, or whose domains have expired (especially if they also aren't on LibGen/Wayback/etc, or on Amazon)?
Arjun Panickssery (arjun-panickssery) · 2024-10-13T20:21:04.540Z · answers+comments (4)
Chevy Bolt Review
jefftk (jkaufman) · 2024-09-26T13:40:05.456Z · comments (2)
[link] Diffusion Guided NLP: better steering, mostly a good thing
Nathan Helm-Burger (nathan-helm-burger) · 2024-08-10T19:49:50.963Z · comments (0)
[link] Metaculus Is Open Source
ChristianWilliams · 2024-10-07T19:55:31.035Z · comments (0)
[link] Sam Altman's Business Negging
Julian Bradshaw · 2024-09-30T21:06:59.184Z · comments (0)
Something Is Lost When AI Makes Art
utilistrutil · 2024-08-18T22:53:46.951Z · comments (0)
← previous page (newer posts) · next page (older posts) →