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) →

Turning Your Back On Traffic
jefftk (jkaufman) · 2024-07-17T01:00:08.627Z · comments (7)
My best guess at the important tricks for training 1L SAEs
Arthur Conmy (arthur-conmy) · 2023-12-21T01:59:06.208Z · comments (4)
[link] Dark Skies Book Review
PeterMcCluskey · 2023-12-29T18:28:59.352Z · comments (3)
Medical Roundup #2
Zvi · 2024-04-09T13:40:05.908Z · comments (18)
Thousands of malicious actors on the future of AI misuse
Zershaaneh Qureshi (zershaaneh-qureshi) · 2024-04-01T10:08:42.357Z · comments (0)
Interview with Vanessa Kosoy on the Value of Theoretical Research for AI
WillPetillo · 2023-12-04T22:58:40.005Z · comments (0)
Otherness and control in the age of AGI
Joe Carlsmith (joekc) · 2024-01-02T18:15:54.168Z · comments (0)
[link] Increasing IQ is trivial
George3d6 · 2024-03-01T22:43:32.037Z · comments (60)
AI #66: Oh to Be Less Online
Zvi · 2024-05-30T14:20:03.334Z · comments (6)
On DeepMind’s Frontier Safety Framework
Zvi · 2024-06-18T13:30:21.154Z · comments (4)
A New Class of Glitch Tokens - BPE Subtoken Artifacts (BSA)
Lao Mein (derpherpize) · 2024-09-20T13:13:26.181Z · comments (7)
[link] Turning 22 in the Pre-Apocalypse
testingthewaters · 2024-08-22T20:28:25.794Z · comments (14)
[link] I didn't have to avoid you; I was just insecure
Chipmonk · 2024-08-17T16:41:50.237Z · comments (7)
Distinguish worst-case analysis from instrumental training-gaming
Olli Järviniemi (jarviniemi) · 2024-09-05T19:13:34.443Z · comments (0)
The murderous shortcut: a toy model of instrumental convergence
Thomas Kwa (thomas-kwa) · 2024-10-02T06:48:06.787Z · comments (0)
[link] A High Decoupling Failure
Maxwell Tabarrok (maxwell-tabarrok) · 2024-04-14T19:46:09.552Z · comments (5)
Your LLM Judge may be biased
Henry Papadatos (henry) · 2024-03-29T16:39:22.534Z · comments (9)
[question] Is there software to practice reading expressions?
lsusr · 2024-04-23T21:53:00.679Z · answers+comments (10)
[link] Twitter thread on AI takeover scenarios
Richard_Ngo (ricraz) · 2024-07-31T00:24:33.866Z · comments (0)
[link] WSJ: Inside Amazon’s Secret Operation to Gather Intel on Rivals
trevor (TrevorWiesinger) · 2024-04-23T21:33:08.049Z · comments (5)
[link] [Fiction] A Confession
Arjun Panickssery (arjun-panickssery) · 2024-04-18T16:28:48.194Z · comments (2)
UDT1.01: The Story So Far (1/10)
Diffractor · 2024-03-27T23:22:35.170Z · comments (6)
AI #49: Bioweapon Testing Begins
Zvi · 2024-02-01T15:30:04.690Z · comments (11)
Free Will and Dodging Anvils: AIXI Off-Policy
Cole Wyeth (Amyr) · 2024-08-29T22:42:24.485Z · comments (12)
Gated Attention Blocks: Preliminary Progress toward Removing Attention Head Superposition
cmathw · 2024-04-08T11:14:43.268Z · comments (4)
Eye contact is effortless when you’re no longer emotionally blocked on it
Chipmonk · 2024-09-27T21:47:01.970Z · comments (24)
[link] Toki pona FAQ
dkl9 · 2024-03-17T21:44:21.782Z · comments (8)
An anti-inductive sequence
Viliam · 2024-08-14T12:28:54.226Z · comments (10)
[link] Claude 3 Opus can operate as a Turing machine
Gunnar_Zarncke · 2024-04-17T08:41:57.209Z · comments (2)
(Appetitive, Consummatory) ≈ (RL, reflex)
Steven Byrnes (steve2152) · 2024-06-15T15:57:39.533Z · comments (1)
But Where do the Variables of my Causal Model come from?
Dalcy (Darcy) · 2024-08-09T22:07:57.395Z · comments (1)
My disagreements with "AGI ruin: A List of Lethalities"
Noosphere89 (sharmake-farah) · 2024-09-15T17:22:18.367Z · comments (46)
Debate: Is it ethical to work at AI capabilities companies?
Ben Pace (Benito) · 2024-08-14T00:18:38.846Z · comments (21)
Good job opportunities for helping with the most important century
HoldenKarnofsky · 2024-01-18T17:30:03.332Z · comments (0)
We’re not as 3-Dimensional as We Think
silentbob · 2024-08-04T14:39:16.799Z · comments (16)
[link] Shifting Headspaces - Transitional Beast-Mode
Jonathan Moregård (JonathanMoregard) · 2024-08-12T13:02:06.120Z · comments (9)
Drone Wars Endgame
RussellThor · 2024-02-01T02:30:46.161Z · comments (71)
The Evolution of Humans Was Net-Negative for Human Values
Zack_M_Davis · 2024-04-01T16:01:10.037Z · comments (1)
On Dwarkesh’s 3rd Podcast With Tyler Cowen
Zvi · 2024-02-02T19:30:05.974Z · comments (9)
[link] "Model UN Solutions"
Arjun Panickssery (arjun-panickssery) · 2023-12-08T23:06:33.490Z · comments (5)
Finding the Wisdom to Build Safe AI
Gordon Seidoh Worley (gworley) · 2024-07-04T19:04:16.089Z · comments (10)
AI companies' commitments
Zach Stein-Perlman · 2024-05-29T11:00:31.339Z · comments (0)
Deeply Cover Car Crashes?
jefftk (jkaufman) · 2023-12-10T22:20:01.133Z · comments (31)
Introduce a Speed Maximum
jefftk (jkaufman) · 2024-01-11T02:50:04.284Z · comments (28)
AI Safety Camp final presentations
Linda Linsefors · 2024-03-29T14:27:43.503Z · comments (3)
List of strategies for mitigating deceptive alignment
joshc (joshua-clymer) · 2023-12-02T05:56:50.867Z · comments (2)
[link] Scaling laws for dominant assurance contracts
jessicata (jessica.liu.taylor) · 2023-11-28T23:11:07.631Z · comments (5)
A Socratic dialogue with my student
lsusr · 2023-12-05T09:31:05.266Z · comments (14)
Childhood and Education Roundup #5
Zvi · 2024-04-17T13:00:03.015Z · comments (4)
Please Bet On My Quantified Self Decision Markets
niplav · 2023-12-01T20:07:38.284Z · comments (6)
← previous page (newer posts) · next page (older posts) →