LessWrong 2.0 Reader

View: New · Old · Top

← previous page (newer posts) · next page (older posts) →

Ways I Expect AI Regulation To Increase Extinction Risk
1a3orn · 2023-07-04T17:32:48.047Z · comments (32)
[link] Apocalypse Prepping - Concise SHTF guide to prepare for AGI doomsday
prepper · 2023-07-04T17:41:41.401Z · comments (9)
Animal Weapons: Lessons for Humans in the Age of X-Risk
Damin Curtis (damin-curtis) · 2023-07-04T18:14:24.166Z · comments (0)
Six (and a half) intuitions for SVD
CallumMcDougall (TheMcDouglas) · 2023-07-04T19:23:19.688Z · comments (1)
Three camps in AI x-risk discussions: My personal very oversimplified overview
Aryeh Englander (alenglander) · 2023-07-04T20:42:12.829Z · comments (0)
[link] Dominant Assurance Contract Experiment #2: Berkeley House Dinners
Arjun Panickssery (arjun-panickssery) · 2023-07-05T00:13:15.255Z · comments (8)
"Reification"
herschel (hrs) · 2023-07-05T00:53:48.984Z · comments (4)
MXR Talkbox Cap?
jefftk (jkaufman) · 2023-07-05T01:50:01.059Z · comments (0)
Final Lightspeed Grants coworking/office hours before the application deadline
habryka (habryka4) · 2023-07-05T06:03:37.649Z · comments (2)
Puffer-pope reality check
Neil (neil-warren) · 2023-07-05T09:27:11.200Z · comments (2)
Optimized for Something other than Winning or: How Cricket Resists Moloch and Goodhart's Law
A.H. (AlfredHarwood) · 2023-07-05T12:33:07.166Z · comments (25)
Exploring Functional Decision Theory (FDT) and a modified version (ModFDT)
MiguelDev (whitehatStoic) · 2023-07-05T14:06:13.870Z · comments (11)
AISN #13: An interdisciplinary perspective on AI proxy failures, new competitors to ChatGPT, and prompting language models to misbehave
Dan H (dan-hendrycks) · 2023-07-05T15:33:19.699Z · comments (0)
[question] What did AI Safety’s specific funding of AGI R&D labs lead to?
Remmelt (remmelt-ellen) · 2023-07-05T15:51:27.286Z · answers+comments (0)
(tentatively) Found 600+ Monosemantic Features in a Small LM Using Sparse Autoencoders
Logan Riggs (elriggs) · 2023-07-05T16:49:43.822Z · comments (1)
The risk-reward tradeoff of interpretability research
JustinShovelain · 2023-07-05T17:05:36.923Z · comments (1)
An AGI kill switch with defined security properties
Peterpiper · 2023-07-05T17:40:05.299Z · comments (6)
[link] If you wish to make an apple pie, you must first become dictator of the universe
jasoncrawford · 2023-07-05T18:14:58.845Z · comments (9)
[link] [Linkpost] Introducing Superalignment
beren · 2023-07-05T18:23:18.419Z · comments (68)
Infra-Bayesian Logic
harfe · 2023-07-05T19:16:41.811Z · comments (2)
Announcing Manifund Regrants
Austin Chen (austin-chen) · 2023-07-05T19:42:08.978Z · comments (8)
AI Intermediation
jefftk (jkaufman) · 2023-07-06T01:50:01.852Z · comments (0)
Distillation: RL with KL penalties is better viewed as Bayesian inference
Nina Rimsky (NinaR) · 2023-07-06T03:33:40.753Z · comments (0)
Open Thread - July 2023
Ruby · 2023-07-06T04:50:06.735Z · comments (35)
Do you feel that AGI Alignment could be achieved in a Type 0 civilization?
Super AGI (super-agi) · 2023-07-06T04:52:57.819Z · comments (1)
AI #19: Hofstadter, Sutskever, Leike
Zvi · 2023-07-06T12:50:05.037Z · comments (16)
Agency begets agency
Richard_Ngo (ricraz) · 2023-07-06T13:08:44.318Z · comments (1)
Announcing the EA Archive
Aaron Bergman (aaronb50) · 2023-07-06T13:49:17.387Z · comments (2)
Understanding the two most common mental health problems in the world
spencerg · 2023-07-06T14:06:25.968Z · comments (0)
[link] A Defense of Work on Mathematical AI Safety
Davidmanheim · 2023-07-06T14:15:21.074Z · comments (13)
Towards Non-Panopticon AI Alignment
Logan Zoellner (logan-zoellner) · 2023-07-06T15:29:39.705Z · comments (0)
[link] Progress links and tweets, 2023-07-06: Terraformer Mark One, Israeli water management, & more
jasoncrawford · 2023-07-06T15:35:22.591Z · comments (4)
[link] Jesse Hoogland on Developmental Interpretability and Singular Learning Theory
Michaël Trazzi (mtrazzi) · 2023-07-06T15:46:00.116Z · comments (2)
Localizing goal misgeneralization in a maze-solving policy network
jan betley (jan-betley) · 2023-07-06T16:21:03.813Z · comments (2)
Layering and Technical Debt in the Global Wayfinding Model
herschel (hrs) · 2023-07-06T17:30:52.645Z · comments (0)
BOUNTY AVAILABLE: AI ethicists, what are your object-level arguments against AI notkilleveryoneism?
Peter Berggren (peter-berggren) · 2023-07-06T17:32:08.675Z · comments (6)
Does biology matter to consciousness?
Reed (ThomasReed) · 2023-07-06T17:38:04.353Z · comments (4)
Progress Studies Fellowship looking for members
jay ram (soycid) · 2023-07-06T17:41:19.125Z · comments (0)
Empirical Evidence Against "The Longest Training Run"
NickGabs · 2023-07-06T18:32:02.754Z · comments (0)
Two paths to win the AGI transition
Nathan Helm-Burger (nathan-helm-burger) · 2023-07-06T21:59:23.150Z · comments (8)
What are the best non-LW places to read on alignment progress?
Raemon · 2023-07-07T00:57:21.417Z · comments (14)
[link] Apparently, of the 195 Million the DoD allocated in University Research Funding Awards in 2022, more than half of them concerned AI or compute hardware research
mako yass (MakoYass) · 2023-07-07T01:20:20.079Z · comments (5)
ask me about technology
bhauth · 2023-07-07T02:03:37.642Z · comments (42)
[question] Can LessWrong provide me with something I find obviously highly useful to my own practical life?
agrippa · 2023-07-07T03:08:58.183Z · answers+comments (4)
Internal independent review for language model agent alignment
Seth Herd · 2023-07-07T06:54:11.552Z · comments (26)
Interpreting Modular Addition in MLPs
Bart Bussmann (Stuckwork) · 2023-07-07T09:22:51.940Z · comments (0)
[link] Passing the ideological Turing test? Arguments against existential risk from AI.
Nina Rimsky (NinaR) · 2023-07-07T10:38:59.829Z · comments (5)
Meetup Tip: Ask Attendees To Explain It
Screwtape · 2023-07-07T16:08:40.639Z · comments (0)
[link] Introducing bayescalc.io
Adele Lopez (adele-lopez-1) · 2023-07-07T16:11:12.854Z · comments (29)
Notes from the Qatar Center for Global Banking and Finance 3rd Annual Conference
PixelatedPenguin · 2023-07-07T23:48:24.560Z · comments (0)
← previous page (newer posts) · next page (older posts) →