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] My AI timelines
xpostah · 2024-12-22T21:06:41.722Z · comments (2)
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)
[question] Do infinite alternatives make AI alignment impossible?
Dakara (chess-ice) · 2024-12-16T18:11:51.233Z · answers+comments (2)
Rethinking Laplace's Rule of Succession
Cleo Nardo (strawberry calm) · 2024-11-22T18:46:25.156Z · comments (5)
How I'd like alignment to get done (as of 2024-10-18)
TristanTrim · 2024-10-18T23:39:03.107Z · comments (4)
Conversational Signposts—An Antidote to Dull Social Interactions
Declan Molony (declan-molony) · 2024-10-22T05:37:56.175Z · comments (6)
Updating the NAO Simulator
jefftk (jkaufman) · 2024-10-30T13:50:06.908Z · comments (0)
Launching Applications for the Global AI Safety Fellowship 2025!
Aditya_SK (team-ai-safety) · 2024-11-30T14:02:16.537Z · comments (5)
Beyond Defensive Technology
ejk64 · 2024-10-14T11:34:24.595Z · comments (1)
[link] Progress links and short notes, 2024-12-27: Clinical trial abundance, grid-scale fusion, permitting vs. compliance, crossword mania, and more
jasoncrawford · 2024-12-27T23:34:43.807Z · comments (0)
[link] Anthropic - The case for targeted regulation
anaguma · 2024-11-05T07:07:48.174Z · comments (0)
[link] LLMs Do Not Think Step-by-step In Implicit Reasoning
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-11-28T09:16:57.463Z · comments (0)
Spooky Recommendation System Scaling
phdead · 2024-10-31T22:00:51.728Z · comments (0)
Reward Bases: A simple mechanism for adaptive acquisition of multiple reward type
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-11-23T12:45:01.067Z · comments (0)
[link] My Mental Model of AI Creativity – Creativity Kiki
Adam Newgas (BorisTheBrave) · 2024-12-09T22:24:23.096Z · comments (0)
[link] The Computational Complexity of Circuit Discovery for Inner Interpretability
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-10-17T13:18:46.378Z · comments (2)
7. Iterate the Game: Racing Where?
Allison Duettmann (allison-duettmann) · 2025-01-02T19:06:22.165Z · comments (0)
Last Line of Defense: Minimum Viable Shelters for Mirror Bacteria
Ulrik Horn (ulrik-horn) · 2024-12-21T08:28:14.860Z · comments (25)
[link] Picking favourites is hard
dkl9 · 2024-12-04T20:46:47.470Z · comments (3)
LDT (and everything else) can be irrational
Christopher King (christopher-king) · 2024-11-06T04:05:36.932Z · comments (7)
Substituting Talkbox for Breath Controller
jefftk (jkaufman) · 2024-10-27T19:10:03.768Z · comments (0)
The Three Warnings of the Zentradi
Trevor Hill-Hand (Jadael) · 2024-11-21T20:28:45.567Z · comments (1)
Fundamental Uncertainty: Chapter 9 - How do we live with uncertainty?
Gordon Seidoh Worley (gworley) · 2024-11-07T18:15:45.049Z · comments (2)
[question] What are some scenarios where an aligned AGI actually helps humanity, but many/most people don't like it?
RomanS · 2025-01-10T18:13:11.900Z · answers+comments (6)
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)
Panology
JenniferRM · 2024-12-23T21:40:14.540Z · comments (8)
Rethink Wellbeing’s Year 2 Update: Foster Sustainable High Performance for Ambitious Altruists
Inga G. (inga-g) · 2024-12-08T14:32:39.902Z · comments (1)
[question] How counterfactual are logical counterfactuals?
Donald Hobson (donald-hobson) · 2024-12-15T21:16:40.515Z · answers+comments (10)
[link] OpenAI’s cybersecurity is probably regulated by NIS Regulations
Adam Jones (domdomegg) · 2024-10-25T11:06:38.392Z · comments (2)
[link] Forecast With GiveWell
ChristianWilliams · 2024-12-11T17:52:32.293Z · comments (0)
Fundamental Uncertainty: Epilogue
Gordon Seidoh Worley (gworley) · 2024-11-16T00:57:48.823Z · comments (0)
[question] LW resources on childhood experiences?
nahir91595 · 2024-10-14T17:04:07.810Z · answers+comments (7)
Prediction markets and Taxes
Edmund Nelson (edmund-nelson) · 2024-11-01T17:39:35.191Z · comments (7)
[link] Bridgewater x Metaculus Forecasting Contest Goes Global — Feb 3, $25k, Opportunities
ChristianWilliams · 2025-01-07T21:40:30.899Z · comments (0)
Festival Stats 2024
jefftk (jkaufman) · 2024-11-12T02:00:04.831Z · comments (0)
Expected Utility, Geometric Utility, and Other Equivalent Representations
StrivingForLegibility · 2024-11-20T23:28:21.826Z · comments (0)
[link] Roots of Progress is hiring an event manager
jasoncrawford · 2024-12-03T20:46:42.929Z · comments (0)
Book review: Range by David Epstein
PatrickDFarley · 2025-01-08T04:27:26.391Z · comments (0)
[link] Chemical Turing Machines
Yudhister Kumar (randomwalks) · 2024-12-03T05:26:25.950Z · comments (2)
[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] o1 tried to avoid being shut down
Raelifin · 2024-12-05T19:52:03.620Z · comments (5)
A Case for Conscious Significance rather than Free Will.
James Stephen Brown (james-brown) · 2024-10-25T23:20:30.834Z · comments (2)
Low Temperature Solomonoff Induction
dil-leik-og (samuel-buteau) · 2024-12-06T18:55:08.948Z · comments (4)
[link] Proposing the Conditional AI Safety Treaty (linkpost TIME)
otto.barten (otto-barten) · 2024-11-15T13:59:01.050Z · comments (8)
Misfortune and Many Worlds
Jonah Wilberg (jrwilb@googlemail.com) · 2024-12-08T20:25:12.109Z · comments (4)
Exporting Facebook Comments, Again
jefftk (jkaufman) · 2024-11-30T12:40:07.339Z · comments (6)
[link] Updating on Bad Arguments
Guive (GAA) · 2024-12-21T01:19:15.686Z · comments (2)
Apply to be a TA for TARA
yanni kyriacos (yanni) · 2024-12-20T02:25:03.514Z · comments (0)
Request for advice: Research for Conversational Game Theory for LLMs
Rome Viharo (rome-viharo) · 2024-10-16T17:53:30.243Z · comments (0)
← previous page (newer posts) · next page (older posts) →