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) →

[link] Can o1-preview find major mistakes amongst 59 NeurIPS '24 MLSB papers?
Abhishaike Mahajan (abhishaike-mahajan) · 2024-12-18T14:21:03.661Z · comments (0)
AGI with RL is Bad News for Safety
Nadav Brandes (nadav-brandes) · 2024-12-21T19:36:03.970Z · comments (17)
Theoretical Alignment's Second Chance
lunatic_at_large · 2024-12-22T05:03:51.653Z · comments (0)
subfunctional overlaps in attentional selection history implies momentum for decision-trajectories
Emrik (Emrik North) · 2024-12-22T14:12:49.027Z · comments (1)
[link] We are in a New Paradigm of AI Progress - OpenAI's o3 model makes huge gains on the toughest AI benchmarks in the world
garrison · 2024-12-22T21:45:52.026Z · comments (3)
[link] A primer on machine learning in cryo-electron microscopy (cryo-EM)
Abhishaike Mahajan (abhishaike-mahajan) · 2024-12-22T15:11:58.860Z · comments (0)
Reality is Fractal-Shaped
silentbob · 2024-12-17T13:52:16.946Z · comments (1)
[link] Funding Case: AI Safety Camp 11
Remmelt (remmelt-ellen) · 2024-12-23T08:51:55.255Z · comments (0)
Everything you care about is in the map
Tahp · 2024-12-17T14:05:36.824Z · comments (27)
[link] Being Present is Not a Skill
Chipmonk · 2024-12-18T01:11:04.715Z · comments (6)
[link] It looks like there are some good funding opportunities in AI safety right now
Benjamin_Todd · 2024-12-22T12:41:02.151Z · comments (0)
[link] Don't Associate AI Safety With Activism
Eneasz · 2024-12-18T08:01:50.357Z · comments (15)
Doing Sport Reliably via Dancing
Johannes C. Mayer (johannes-c-mayer) · 2024-12-20T12:06:59.517Z · comments (0)
[link] o3 is not being released to the public. First they are only giving access to external safety testers. You can apply to get early access to do safety testing
KatWoods (ea247) · 2024-12-20T18:30:44.421Z · comments (0)
[link] The Genesis Project
aproteinengine · 2024-12-19T21:26:51.344Z · comments (0)
Stop Making Sense
JenniferRM · 2024-12-23T05:16:12.428Z · comments (0)
I'm Writing a Book About Liberalism
Yoav Ravid · 2024-12-19T00:13:33.895Z · comments (6)
[question] What Have Been Your Most Valuable Casual Conversations At Conferences?
johnswentworth · 2024-12-25T05:49:36.711Z · answers+comments (3)
How I saved 1 human life (in expectation) without overthinking it
Christopher King (christopher-king) · 2024-12-22T20:53:13.492Z · comments (0)
Mid-Generation Self-Correction: A Simple Tool for Safer AI
MrThink (ViktorThink) · 2024-12-19T23:41:00.702Z · comments (0)
Robbin's Farm Sledding Route
jefftk (jkaufman) · 2024-12-21T22:10:01.175Z · comments (1)
[link] AISN #45: Center for AI Safety 2024 Year in Review
Corin Katzke (corin-katzke) · 2024-12-19T18:15:56.416Z · comments (0)
How Much to Give is a Pragmatic Question
jefftk (jkaufman) · 2024-12-24T04:20:01.480Z · comments (1)
[link] My AI timelines
xpostah · 2024-12-22T21:06:41.722Z · comments (2)
No Internally-Crispy Mac and Cheese
jefftk (jkaufman) · 2024-12-20T03:20:01.798Z · comments (5)
Simple Steganographic Computation Eval - gpt-4o and gemini-exp-1206 can't solve it yet
Filip Sondej · 2024-12-19T15:47:05.512Z · comments (2)
Preliminary Thoughts on Flirting Theory
la .alis. (Diatom) · 2024-12-24T07:37:47.045Z · comments (4)
Last Line of Defense: Minimum Viable Shelters for Mirror Bacteria
Ulrik Horn (ulrik-horn) · 2024-12-21T08:28:14.860Z · comments (19)
Apply to the 2025 PIBBSS Summer Research Fellowship
DusanDNesic · 2024-12-24T10:25:12.882Z · comments (0)
Do you need a better map of your myriad of maps to the territory?
CstineSublime · 2024-12-24T02:00:30.426Z · comments (2)
Apply now to SPAR!
agucova · 2024-12-19T22:29:58.963Z · comments (0)
[link] What is "wireheading"?
Vishakha (vishakha-agrawal) · 2024-12-17T07:49:50.957Z · comments (0)
[link] Bird's eye view: An interactive representation to see large collection of text "from above".
Alexandre Variengien (alexandre-variengien) · 2024-12-21T00:15:02.239Z · comments (4)
[link] Ideologies are slow and necessary, for now
Gabriel Alfour (gabriel-alfour-1) · 2024-12-23T01:57:47.153Z · comments (1)
Acknowledging Background Information with P(Q|I)
JenniferRM · 2024-12-24T18:50:25.323Z · comments (1)
Notes from Copenhagen Secular Solstice 2024
Søren Elverlin (soren-elverlin-1) · 2024-12-22T15:08:20.848Z · comments (0)
Panology
JenniferRM · 2024-12-23T21:40:14.540Z · comments (8)
Executive Director for AIS France - Expression of interest
gergogaspar (gergo-gaspar) · 2024-12-19T08:14:54.023Z · comments (0)
Near- and medium-term AI Control Safety Cases
Martín Soto (martinsq) · 2024-12-23T17:37:48.860Z · comments (0)
[link] Updating on Bad Arguments
Guive (GAA) · 2024-12-21T01:19:15.686Z · comments (2)
What conclusions can be drawn from a single observation about wealth in tennis?
Trevor Cappallo (trevor-cappallo) · 2024-12-18T09:55:34.923Z · comments (3)
Where do you put your ideas?
CstineSublime · 2024-12-17T07:26:06.685Z · comments (12)
[question] Recommendations on communities that discuss AI applications in society
Annapurna (jorge-velez) · 2024-12-24T13:37:49.821Z · answers+comments (1)
Better difference-making views
MichaelStJules · 2024-12-21T18:27:45.552Z · comments (0)
Reduce AI Self-Allegiance by saying "he" instead of "I"
Knight Lee (Max Lee) · 2024-12-23T09:32:29.947Z · comments (1)
[question] Why is neuron count of human brain relevant to AI timelines?
xpostah · 2024-12-24T05:15:58.839Z · answers+comments (2)
Replaceable Axioms give more credence than irreplaceable axioms
Yoav Ravid · 2024-12-20T00:51:13.578Z · comments (2)
A short critique of Omohundro's "Basic AI Drives"
Soumyadeep Bose (soumyadeep-bose) · 2024-12-19T19:19:52.864Z · comments (0)
Printable book of some rationalist creative writing (from Scott A. & Eliezer)
CounterBlunder · 2024-12-23T15:44:31.437Z · comments (0)
1 What If We Rebuild Motivation with the Fermi ESTIMATion?
P. João (gabriel-brito) · 2024-12-17T07:46:40.547Z · comments (0)
← previous page (newer posts) · next page (older posts) →