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) →

I'm creating a deep dive podcast episode about the original Leverage Research - would you like to take part?
spencerg · 2024-09-22T14:03:22.164Z · comments (2)
Distinguish worst-case analysis from instrumental training-gaming
Olli Järviniemi (jarviniemi) · 2024-09-05T19:13:34.443Z · comments (0)
Glitch Token Catalog - (Almost) a Full Clear
Lao Mein (derpherpize) · 2024-09-21T12:22:16.403Z · comments (3)
LASR Labs Spring 2025 applications are open!
Erin Robertson · 2024-10-04T13:44:20.524Z · comments (0)
A New Class of Glitch Tokens - BPE Subtoken Artifacts (BSA)
Lao Mein (derpherpize) · 2024-09-20T13:13:26.181Z · comments (7)
AI Safety Camp 10
Robert Kralisch (nonmali-1) · 2024-10-26T11:08:09.887Z · comments (7)
Exploring SAE features in LLMs with definition trees and token lists
mwatkins · 2024-10-04T22:15:28.108Z · comments (5)
COT Scaling implies slower takeoff speeds
Logan Zoellner (logan-zoellner) · 2024-09-28T16:20:00.320Z · comments (56)
OODA your OODA Loop
Raemon · 2024-10-11T00:50:48.119Z · comments (3)
The murderous shortcut: a toy model of instrumental convergence
Thomas Kwa (thomas-kwa) · 2024-10-02T06:48:06.787Z · comments (0)
Is the Power Grid Sustainable?
jefftk (jkaufman) · 2024-10-26T02:30:06.612Z · comments (37)
[link] Big tech transitions are slow (with implications for AI)
jasoncrawford · 2024-10-24T14:25:06.873Z · comments (16)
Eye contact is effortless when you’re no longer emotionally blocked on it
Chipmonk · 2024-09-27T21:47:01.970Z · comments (24)
Video and transcript of presentation on Otherness and control in the age of AGI
Joe Carlsmith (joekc) · 2024-10-08T22:30:38.054Z · comments (1)
Book Review: On the Edge: The Gamblers
Zvi · 2024-09-24T11:50:06.065Z · comments (1)
Open Problems in AIXI Agent Foundations
Cole Wyeth (Amyr) · 2024-09-12T15:38:59.007Z · comments (2)
Monthly Roundup #22: September 2024
Zvi · 2024-09-17T12:20:08.297Z · comments (10)
[link] On Fables and Nuanced Charts
Niko_McCarty (niko-2) · 2024-09-08T17:09:07.503Z · comments (2)
AI #89: Trump Card
Zvi · 2024-11-07T16:30:05.684Z · comments (12)
The Cognitive Bootcamp Agreement
Raemon · 2024-10-16T23:24:05.509Z · comments (0)
[question] If I have some money, whom should I donate it to in order to reduce expected P(doom) the most?
KvmanThinking (avery-liu) · 2024-10-03T11:31:19.974Z · answers+comments (36)
Live Machinery: An Interface Design Philosophy for Wholesome AI Futures (Workshop @ EA Hotel!)
Sahil · 2024-11-01T17:24:09.957Z · comments (2)
Augmenting Statistical Models with Natural Language Parameters
jsteinhardt · 2024-09-20T18:30:10.816Z · comments (0)
ARENA4.0 Capstone: Hyperparameter tuning for MELBO + replication on Llama-3.2-1b-Instruct
25Hour (aaron-kaufman) · 2024-10-05T11:30:11.953Z · comments (2)
(Maybe) A Bag of Heuristics is All There Is & A Bag of Heuristics is All You Need
Sodium · 2024-10-03T19:11:58.032Z · comments (17)
What AI companies should do: Some rough ideas
Zach Stein-Perlman · 2024-10-21T14:00:10.412Z · comments (10)
[link] Information dark matter
Logan Kieller (logan-kieller) · 2024-10-01T15:05:41.159Z · comments (4)
Empathy/Systemizing Quotient is a poor/biased model for the autism/sex link
tailcalled · 2024-11-04T21:11:57.788Z · comments (0)
My disagreements with "AGI ruin: A List of Lethalities"
Noosphere89 (sharmake-farah) · 2024-09-15T17:22:18.367Z · comments (44)
Proveably Safe Self Driving Cars [Modulo Assumptions]
Davidmanheim · 2024-09-15T13:58:19.472Z · comments (26)
Intent alignment as a stepping-stone to value alignment
Seth Herd · 2024-11-05T20:43:24.950Z · comments (4)
[link] Concrete benefits of making predictions
Jonny Spicer (jonnyspicer) · 2024-10-17T14:23:17.613Z · comments (5)
Housing Roundup #10
Zvi · 2024-10-29T13:50:09.416Z · comments (2)
RLHF is the worst possible thing done when facing the alignment problem
tailcalled · 2024-09-19T18:56:27.676Z · comments (10)
[link] NAO Updates, Fall 2024
jefftk (jkaufman) · 2024-10-18T00:00:04.142Z · comments (2)
A path to human autonomy
Nathan Helm-Burger (nathan-helm-burger) · 2024-10-29T03:02:42.475Z · comments (12)
DunCon @Lighthaven
Duncan Sabien (Deactivated) (Duncan_Sabien) · 2024-09-29T04:56:27.205Z · comments (0)
An argument that consequentialism is incomplete
cousin_it · 2024-10-07T09:45:12.754Z · comments (27)
Resolving von Neumann-Morgenstern Inconsistent Preferences
niplav · 2024-10-22T11:45:20.915Z · comments (3)
[link] What is it like to be psychologically healthy? Podcast ft. DaystarEld
Chipmonk · 2024-10-05T19:14:04.743Z · comments (8)
[question] When is reward ever the optimization target?
Noosphere89 (sharmake-farah) · 2024-10-15T15:09:20.912Z · answers+comments (12)
The slingshot helps with learning
Wilson Wu (wilson-wu) · 2024-10-31T23:18:16.762Z · comments (0)
[question] Feedback request: what am I missing?
Nathan Helm-Burger (nathan-helm-burger) · 2024-11-02T17:38:39.625Z · answers+comments (5)
Book Review: What Even Is Gender?
Joey Marcellino · 2024-09-01T16:09:27.773Z · comments (14)
Apply to MATS 7.0!
Ryan Kidd (ryankidd44) · 2024-09-21T00:23:49.778Z · comments (0)
[link] Stone Age Herbalist's notes on ant warfare and slavery
trevor (TrevorWiesinger) · 2024-11-09T02:40:01.128Z · comments (0)
Meme Talking Points
ymeskhout · 2024-11-06T15:27:54.024Z · comments (0)
Context-dependent consequentialism
Jeremy Gillen (jeremy-gillen) · 2024-11-04T09:29:24.310Z · comments (2)
[question] What's the Deal with Logical Uncertainty?
Ape in the coat · 2024-09-16T08:11:43.588Z · answers+comments (23)
Balancing Label Quantity and Quality for Scalable Elicitation
Alex Mallen (alex-mallen) · 2024-10-24T16:49:00.939Z · comments (1)
← previous page (newer posts) · next page (older posts) →