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) →

Do sparse autoencoders find "true features"?
Demian Till · 2024-02-22T18:06:59.630Z · comments (33)
AI for Bio: State Of The Field
sarahconstantin · 2024-08-30T18:00:02.187Z · comments (2)
If we solve alignment, do we die anyway?
Seth Herd · 2024-08-23T13:13:10.933Z · comments (65)
[link] The True Story of How GPT-2 Became Maximally Lewd
Writer · 2024-01-18T21:03:08.167Z · comments (7)
“Artificial General Intelligence”: an extremely brief FAQ
Steven Byrnes (steve2152) · 2024-03-11T17:49:02.496Z · comments (6)
[link] Yoshua Bengio: Reasoning through arguments against taking AI safety seriously
Judd Rosenblatt (judd) · 2024-07-11T23:53:17.187Z · comments (3)
Dumbing down
Martin Sustrik (sustrik) · 2024-06-09T06:50:47.469Z · comments (0)
[link] OpenAI: Preparedness framework
Zach Stein-Perlman · 2023-12-18T18:30:10.153Z · comments (23)
[link] If far-UV is so great, why isn't it everywhere?
Austin Chen (austin-chen) · 2024-10-19T18:56:58.910Z · comments (23)
Instruction-following AGI is easier and more likely than value aligned AGI
Seth Herd · 2024-05-15T19:38:03.185Z · comments (25)
Update on Chinese IQ-related gene panels
Lao Mein (derpherpize) · 2023-12-14T10:12:21.212Z · comments (7)
Epistemic Hell
rogersbacon · 2024-01-27T17:13:09.578Z · comments (20)
Adam Optimizer Causes Privileged Basis in Transformer LM Residual Stream
Diego Caples (diego-caples) · 2024-09-06T17:55:34.265Z · comments (7)
[link] [Repost] The Copenhagen Interpretation of Ethics
mesaoptimizer · 2024-01-25T15:20:08.162Z · comments (4)
Transcoders enable fine-grained interpretable circuit analysis for language models
Jacob Dunefsky (jacob-dunefsky) · 2024-04-30T17:58:09.982Z · comments (14)
[link] [Paper] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
chanind · 2024-09-25T09:31:03.296Z · comments (15)
Flagging Potentially Unfair Parenting
jefftk (jkaufman) · 2023-12-26T12:40:05.099Z · comments (1)
[link] InterLab – a toolkit for experiments with multi-agent interactions
Tomáš Gavenčiak (tomas-gavenciak) · 2024-01-22T18:23:35.661Z · comments (0)
[link] Motivation gaps: Why so much EA criticism is hostile and lazy
titotal (lombertini) · 2024-04-22T11:49:59.389Z · comments (5)
[link] [Link Post] "Foundational Challenges in Assuring Alignment and Safety of Large Language Models"
David Scott Krueger (formerly: capybaralet) (capybaralet) · 2024-06-06T18:55:09.151Z · comments (2)
AXRP Episode 27 - AI Control with Buck Shlegeris and Ryan Greenblatt
DanielFilan · 2024-04-11T21:30:04.244Z · comments (10)
[link] The Inner Ring by C. S. Lewis
Saul Munn (saul-munn) · 2024-04-24T22:48:09.228Z · comments (6)
[link] Davidad's Provably Safe AI Architecture - ARIA's Programme Thesis
simeon_c (WayZ) · 2024-02-01T21:30:44.090Z · comments (17)
Game Theory without Argmax [Part 1]
Cleo Nardo (strawberry calm) · 2023-11-11T15:59:47.486Z · comments (18)
[link] Former OpenAI Superalignment Researcher: Superintelligence by 2030
Julian Bradshaw · 2024-06-05T03:35:19.251Z · comments (30)
Multiplex Gene Editing: Where Are We Now?
sarahconstantin · 2024-07-16T20:50:04.590Z · comments (6)
Finding Sparse Linear Connections between Features in LLMs
Logan Riggs (elriggs) · 2023-12-09T02:27:42.456Z · comments (5)
How We Picture Bayesian Agents
johnswentworth · 2024-04-08T18:12:48.595Z · comments (14)
[link] We're all in this together
Tamsin Leake (carado-1) · 2023-12-05T13:57:46.270Z · comments (65)
How useful is "AI Control" as a framing on AI X-Risk?
habryka (habryka4) · 2024-03-14T18:06:30.459Z · comments (4)
[link] Gwern: Why So Few Matt Levines?
kave · 2024-10-29T01:07:27.564Z · comments (8)
[link] The 2nd Demographic Transition
Maxwell Tabarrok (maxwell-tabarrok) · 2024-04-06T14:10:13.095Z · comments (17)
When Are Circular Definitions A Problem?
johnswentworth · 2024-05-28T20:00:23.408Z · comments (15)
AI #79: Ready for Some Football
Zvi · 2024-08-29T13:30:10.902Z · comments (16)
Generalized Stat Mech: The Boltzmann Approach
David Lorell · 2024-04-12T17:47:31.880Z · comments (7)
Text Posts from the Kids Group: 2020
jefftk (jkaufman) · 2024-04-13T22:30:05.326Z · comments (3)
Best in Class Life Improvement
sapphire (deluks917) · 2024-04-04T01:51:02.556Z · comments (20)
The Hessian rank bounds the learning coefficient
Lucius Bushnaq (Lblack) · 2024-08-08T20:55:36.960Z · comments (9)
[link] GPT-4o System Card
Zach Stein-Perlman · 2024-08-08T20:30:52.633Z · comments (11)
Estimating Tail Risk in Neural Networks
Mark Xu (mark-xu) · 2024-09-13T20:00:06.921Z · comments (9)
Different senses in which two AIs can be “the same”
Vivek Hebbar (Vivek) · 2024-06-24T03:16:43.400Z · comments (0)
[Summary] Progress Update #1 from the GDM Mech Interp Team
Neel Nanda (neel-nanda-1) · 2024-04-19T19:06:17.755Z · comments (0)
Duct Tape security
Isaac King (KingSupernova) · 2024-04-26T18:57:05.659Z · comments (11)
What is it to solve the alignment problem?
Joe Carlsmith (joekc) · 2024-08-24T21:19:34.280Z · comments (17)
Alignment can improve generalisation through more robustly doing what a human wants - CoinRun example
Stuart_Armstrong · 2023-11-21T11:41:34.798Z · comments (9)
MATS AI Safety Strategy Curriculum
Ronny Fernandez (ronny-fernandez) · 2024-03-07T19:59:37.434Z · comments (2)
Shard Theory - is it true for humans?
Rishika (rishika-bose) · 2024-06-14T19:21:47.997Z · comments (7)
Meetup Tip: Heartbeat Messages
Screwtape · 2023-12-07T17:18:33.582Z · comments (4)
[New Feature] Your Subscribed Feed
Ruby · 2024-06-11T22:45:00.000Z · comments (8)
Brief notes on the Wikipedia game
Olli Järviniemi (jarviniemi) · 2024-07-14T02:28:22.473Z · comments (9)
← previous page (newer posts) · next page (older posts) →