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] Announcing the Q1 2025 Long-Term Future Fund grant round
Linch · 2024-12-20T02:20:22.448Z · comments (0)
A Sober Look at Steering Vectors for LLMs
Joschka Braun (joschka-braun) · 2024-11-23T17:30:00.745Z · comments (0)
If all trade is voluntary, then what is "exploitation?"
Darmani · 2024-12-27T11:21:30.036Z · comments (59)
Compute and size limits on AI are the actual danger
Shmi (shminux) · 2024-11-23T21:29:37.433Z · comments (5)
Housing Roundup #10
Zvi · 2024-10-29T13:50:09.416Z · comments (2)
[link] Stone Age Herbalist's notes on ant warfare and slavery
trevor (TrevorWiesinger) · 2024-11-09T02:40:01.128Z · comments (0)
RLHF is the worst possible thing done when facing the alignment problem
tailcalled · 2024-09-19T18:56:27.676Z · comments (10)
[question] What's the Deal with Logical Uncertainty?
Ape in the coat · 2024-09-16T08:11:43.588Z · answers+comments (28)
An argument that consequentialism is incomplete
cousin_it · 2024-10-07T09:45:12.754Z · comments (27)
[Letter] Chinese Quickstart
lsusr · 2024-12-01T06:38:15.796Z · comments (0)
[question] What is MIRI currently doing?
Roko · 2024-12-14T02:39:20.886Z · answers+comments (14)
AI #90: The Wall
Zvi · 2024-11-14T14:10:04.562Z · comments (6)
XX by Rian Hughes: Pretentious Bullshit
Yair Halberstadt (yair-halberstadt) · 2025-01-08T13:02:52.438Z · comments (5)
Resolving von Neumann-Morgenstern Inconsistent Preferences
niplav · 2024-10-22T11:45:20.915Z · comments (5)
1. Meet the Players: Value Diversity
Allison Duettmann (allison-duettmann) · 2025-01-02T19:00:52.696Z · comments (2)
Incentive design and capability elicitation
Joe Carlsmith (joekc) · 2024-11-12T20:56:05.088Z · comments (0)
Context-dependent consequentialism
Jeremy Gillen (jeremy-gillen) · 2024-11-04T09:29:24.310Z · comments (6)
Apply to MATS 7.0!
Ryan Kidd (ryankidd44) · 2024-09-21T00:23:49.778Z · comments (0)
[link] What is it like to be psychologically healthy? Podcast ft. DaystarEld
Chipmonk · 2024-10-05T19:14:04.743Z · comments (8)
Balancing Label Quantity and Quality for Scalable Elicitation
Alex Mallen (alex-mallen) · 2024-10-24T16:49:00.939Z · comments (1)
[link] A progress policy agenda
jasoncrawford · 2024-12-19T18:42:37.327Z · comments (1)
A Principled Cartoon Guide to NVC
plex (ete) · 2025-01-07T21:01:07.904Z · comments (5)
[link] Safety tax functions
owencb · 2024-10-20T14:08:38.099Z · comments (0)
AI Safety Seed Funding Network - Join as a Donor or Investor
Alexandra Bos (AlexandraB) · 2024-12-16T19:30:43.812Z · comments (0)
[link] What I expected from this site: A LessWrong review
Nathan Young · 2024-12-20T11:27:39.683Z · comments (5)
AI #85: AI Wins the Nobel Prize
Zvi · 2024-10-10T13:40:07.286Z · comments (6)
Call for evaluators: Participate in the European AI Office workshop on general-purpose AI models and systemic risks
Tom DAVID (tom-david) · 2024-11-27T02:54:16.263Z · comments (0)
People aren't properly calibrated on FrontierMath
cakubilo · 2024-12-23T19:35:44.467Z · comments (4)
[question] Why are there no interesting (1D, 2-state) quantum cellular automata?
Optimization Process · 2024-11-26T00:11:37.833Z · answers+comments (13)
The new ruling philosophy regarding AI
Mitchell_Porter · 2024-11-11T13:28:24.476Z · comments (0)
Two Weeks Without Sweets
jefftk (jkaufman) · 2024-12-31T03:30:02.003Z · comments (0)
[question] Where to find reliable reviews of AI products?
Elizabeth (pktechgirl) · 2024-09-17T23:48:25.899Z · answers+comments (6)
[link] A new process for mapping discussions
Nathan Young · 2024-09-30T08:57:20.029Z · comments (8)
[link] Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
Abhishaike Mahajan (abhishaike-mahajan) · 2024-11-05T14:51:41.310Z · comments (1)
[link] My Methodological Turn
adamShimi · 2024-09-29T15:01:45.986Z · comments (0)
Examples of How I Use LLMs
jefftk (jkaufman) · 2024-10-14T17:10:04.597Z · comments (2)
Aligning AI Safety Projects with a Republican Administration
Deric Cheng (deric-cheng) · 2024-11-21T22:12:27.502Z · comments (1)
[link] Evaluating Synthetic Activations composed of SAE Latents in GPT-2
Giorgi Giglemiani (Rakh) · 2024-09-25T20:37:48.227Z · comments (0)
Acknowledging Background Information with P(Q|I)
JenniferRM · 2024-12-24T18:50:25.323Z · comments (8)
You can validly be seen and validated by a chatbot
Kaj_Sotala · 2024-12-20T12:00:03.015Z · comments (3)
[link] AI & wisdom 1: wisdom, amortised optimisation, and AI
L Rudolf L (LRudL) · 2024-10-28T21:02:51.215Z · comments (0)
MATS mentor selection
DanielFilan · 2025-01-10T03:12:52.141Z · comments (1)
Concrete Methods for Heuristic Estimation on Neural Networks
Oliver Daniels (oliver-daniels-koch) · 2024-11-14T05:07:55.240Z · comments (0)
Distinguishing ways AI can be "concentrated"
Matthew Barnett (matthew-barnett) · 2024-10-21T22:21:13.666Z · comments (2)
First Solo Bus Ride
jefftk (jkaufman) · 2024-12-03T12:20:02.344Z · comments (1)
[link] If-Then Commitments for AI Risk Reduction [by Holden Karnofsky]
habryka (habryka4) · 2024-09-13T19:38:53.194Z · comments (0)
Towards Quantitative AI Risk Management
Henry Papadatos (henry) · 2024-10-16T19:26:48.817Z · comments (1)
Option control
Joe Carlsmith (joekc) · 2024-11-04T17:54:03.073Z · comments (0)
Two flavors of computational functionalism
EuanMcLean (euanmclean) · 2024-11-25T10:47:04.584Z · comments (9)
Corrigibility's Desirability is Timing-Sensitive
RobertM (T3t) · 2024-12-26T22:24:17.435Z · comments (4)
← previous page (newer posts) · next page (older posts) →