LessWrong 2.0 Reader

View: New · Old · Top

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

Bandwagon effect: Bias in Evaluating AGI X-Risks
Remmelt (remmelt-ellen) · 2022-12-28T07:54:50.669Z · comments (0)
Getting up to Speed on the Speed Prior in 2022
robertzk (Technoguyrob) · 2022-12-28T07:49:22.948Z · comments (5)
[question] [link] World superpowers, particularly the United States, still maintain large conventional militaries despite nuclear deterrence. Why?
niederman · 2022-12-28T05:38:15.585Z · answers+comments (8)
[question] What does "probability" really mean?
sisyphus (benj) · 2022-12-28T03:20:45.651Z · answers+comments (20)
Zooming the Chrome Audio Player
jefftk (jkaufman) · 2022-12-28T02:30:01.244Z · comments (0)
What AI Safety Materials Do ML Researchers Find Compelling?
Vael Gates · 2022-12-28T02:03:31.894Z · comments (34)
South Bay ACX/LW Meetup
IS (is) · 2022-12-28T01:59:12.389Z · comments (0)
Regarding Blake Lemoine's claim that LaMDA is 'sentient', he might be right (sorta), but perhaps not for the reasons he thinks
philosophybear · 2022-12-28T01:55:40.565Z · comments (1)
Fundamental Uncertainty: Chapter 5 - How do we know what we know?
Gordon Seidoh Worley (gworley) · 2022-12-28T01:28:50.605Z · comments (2)
Is checking that a state of the world is not dystopian easier than constructing a non-dystopian state?
No77e (no77e-noi) · 2022-12-27T20:57:27.663Z · comments (3)
Crypto-currency as pro-alignment mechanism
False Name (False Name, Esq.) · 2022-12-27T17:45:54.474Z · comments (2)
[link] My Reservations about Discovering Latent Knowledge (Burns, Ye, et al)
Robert_AIZI · 2022-12-27T17:27:02.225Z · comments (0)
[link] Things that can kill you quickly: What everyone should know about first aid
jasoncrawford · 2022-12-27T16:23:24.831Z · comments (21)
[question] Why The Focus on Expected Utility Maximisers?
DragonGod · 2022-12-27T15:49:36.536Z · answers+comments (84)
[link] Presumptive Listening: sticking to familiar concepts and missing the outer reasoning paths
Remmelt (remmelt-ellen) · 2022-12-27T15:40:23.698Z · comments (8)
Mere exposure effect: Bias in Evaluating AGI X-Risks
Remmelt (remmelt-ellen) · 2022-12-27T14:05:29.563Z · comments (2)
Housing and Transportation Roundup #2
Zvi · 2022-12-27T13:10:00.979Z · comments (0)
[question] Are tulpas moral patients?
ChristianKl · 2022-12-27T11:30:29.923Z · answers+comments (28)
Reflections on my 5-month alignment upskilling grant
Jay Bailey · 2022-12-27T10:51:49.872Z · comments (4)
[link] Institutions Cannot Restrain Dark-Triad AI Exploitation
Remmelt (remmelt-ellen) · 2022-12-27T10:34:34.698Z · comments (0)
Introduction: Bias in Evaluating AGI X-Risks
Remmelt (remmelt-ellen) · 2022-12-27T10:27:30.646Z · comments (0)
MDPs and the Bellman Equation, Intuitively Explained
Jack O'Brien (jack-o-brien) · 2022-12-27T05:50:23.633Z · comments (3)
[link] How 'Human-Human' dynamics give way to 'Human-AI' and then 'AI-AI' dynamics
Remmelt (remmelt-ellen) · 2022-12-27T03:16:17.377Z · comments (5)
[link] Nine Points of Collective Insanity
Remmelt (remmelt-ellen) · 2022-12-27T03:14:11.426Z · comments (3)
Fractional Resignation
jefftk (jkaufman) · 2022-12-27T02:30:01.240Z · comments (6)
[question] What policies have most thoroughly crippled (otherwise-promising) industries or technologies?
benwr · 2022-12-27T02:25:44.376Z · answers+comments (4)
Recent advances in Natural Language Processing—Some Woolly speculations (2019 essay on semantics and language models)
philosophybear · 2022-12-27T02:11:36.960Z · comments (0)
Against Agents as an Approach to Aligned Transformative AI
DragonGod · 2022-12-27T00:47:03.706Z · comments (9)
Can we efficiently distinguish different mechanisms?
paulfchristiano · 2022-12-27T00:20:01.728Z · comments (30)
Air-gapping evaluation and support
Ryan Kidd (ryankidd44) · 2022-12-26T22:52:29.881Z · comments (1)
Slightly against aligning with neo-luddites
Matthew Barnett (matthew-barnett) · 2022-12-26T22:46:42.693Z · comments (31)
Avoiding perpetual risk from TAI
scasper · 2022-12-26T22:34:48.565Z · comments (6)
Announcing: The Independent AI Safety Registry
Shoshannah Tekofsky (DarkSym) · 2022-12-26T21:22:18.381Z · comments (9)
Are men harder to help?
braces · 2022-12-26T21:11:08.036Z · comments (1)
[question] How much should I update on the fact that my dentist is named Dennis?
MichaelDickens · 2022-12-26T19:11:07.918Z · answers+comments (3)
[link] Theodicy and the simulation hypothesis, or: The problem of simulator evil
philosophybear · 2022-12-26T18:55:15.872Z · comments (12)
[link] Safety of Self-Assembled Neuromorphic Hardware
Can (Can Rager) · 2022-12-26T18:51:26.163Z · comments (2)
Coherent extrapolated dreaming
Alex Flint (alexflint) · 2022-12-26T17:29:14.420Z · comments (10)
An overview of some promising work by junior alignment researchers
Akash (akash-wasil) · 2022-12-26T17:23:58.991Z · comments (0)
Solstice song: Here Lies the Dragon
jchan · 2022-12-26T16:08:34.740Z · comments (1)
The Usefulness Paradigm
Aprillion (Peter Hozák) (Aprillion) · 2022-12-26T13:23:58.722Z · comments (4)
Looking Back on Posts From 2022
Zvi · 2022-12-26T13:20:00.745Z · comments (8)
[link] Analogies between Software Reverse Engineering and Mechanistic Interpretability
Neel Nanda (neel-nanda-1) · 2022-12-26T12:26:57.880Z · comments (6)
Mlyyrczo
lsusr · 2022-12-26T07:58:57.920Z · comments (14)
Causal abstractions vs infradistributions
Pablo Villalobos (pvs) · 2022-12-26T00:21:16.179Z · comments (0)
[link] Concrete Steps to Get Started in Transformer Mechanistic Interpretability
Neel Nanda (neel-nanda-1) · 2022-12-25T22:21:49.686Z · comments (7)
It's time to worry about online privacy again
Malmesbury (Elmer of Malmesbury) · 2022-12-25T21:05:30.977Z · comments (23)
[link] [Hebbian Natural Abstractions] Mathematical Foundations
Samuel Nellessen (samuel-nellessen) · 2022-12-25T20:58:03.423Z · comments (2)
[question] Oracle AGI - How can it escape, other than security issues? (Steganography?)
RationalSieve · 2022-12-25T20:14:09.834Z · answers+comments (6)
YCombinator fraud rates
Xodarap · 2022-12-25T19:21:52.829Z · comments (3)
← previous page (newer posts) · next page (older posts) →