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) →

Meme Talking Points
ymeskhout · 2024-11-06T15:27:54.024Z · comments (0)
[link] What is it like to be psychologically healthy? Podcast ft. DaystarEld
Chipmonk · 2024-10-05T19:14:04.743Z · comments (8)
Basics of Handling Disagreements with People
Camille Berger (Camille Berger) · 2024-11-12T17:55:08.143Z · comments (2)
Bay Winter Solstice 2024: Speech Auditions
ozymandias · 2024-11-04T22:31:38.680Z · comments (0)
[question] When is reward ever the optimization target?
Noosphere89 (sharmake-farah) · 2024-10-15T15:09:20.912Z · answers+comments (12)
[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)
Incentive design and capability elicitation
Joe Carlsmith (joekc) · 2024-11-12T20:56:05.088Z · comments (0)
[link] [Paper] Hidden in Plain Text: Emergence and Mitigation of Steganographic Collusion in LLMs
Yohan Mathew (ymath) · 2024-09-25T14:52:48.263Z · comments (2)
Fun With CellxGene
sarahconstantin · 2024-09-06T22:00:03.461Z · comments (2)
AI #85: AI Wins the Nobel Prize
Zvi · 2024-10-10T13:40:07.286Z · comments (6)
Open Thread Fall 2024
habryka (habryka4) · 2024-10-05T22:28:50.398Z · comments (109)
5 ways to improve CoT faithfulness
CBiddulph (caleb-biddulph) · 2024-10-05T20:17:12.637Z · comments (8)
[link] Safety tax functions
owencb · 2024-10-20T14:08:38.099Z · comments (0)
[link] Why Recursion Pharmaceuticals abandoned cell painting for brightfield imaging
Abhishaike Mahajan (abhishaike-mahajan) · 2024-11-05T14:51:41.310Z · comments (1)
Examples of How I Use LLMs
jefftk (jkaufman) · 2024-10-14T17:10:04.597Z · comments (2)
[link] Liquid vs Illiquid Careers
vaishnav92 · 2024-10-20T23:03:49.725Z · comments (6)
[question] Where to find reliable reviews of AI products?
Elizabeth (pktechgirl) · 2024-09-17T23:48:25.899Z · answers+comments (6)
Searching for phenomenal consciousness in LLMs: Perceptual reality monitoring and introspective confidence
EuanMcLean (euanmclean) · 2024-10-29T12:16:18.448Z · comments (7)
[link] My Methodological Turn
adamShimi · 2024-09-29T15:01:45.986Z · comments (0)
[link] AI forecasting bots incoming
Dan H (dan-hendrycks) · 2024-09-09T19:14:31.050Z · comments (44)
[link] AI Safety at the Frontier: Paper Highlights, August '24
gasteigerjo · 2024-09-03T19:17:24.850Z · comments (0)
Towards Quantitative AI Risk Management
Henry Papadatos (henry) · 2024-10-16T19:26:48.817Z · comments (1)
[link] A new process for mapping discussions
Nathan Young · 2024-09-30T08:57:20.029Z · comments (7)
Trading Candy
jefftk (jkaufman) · 2024-11-01T01:10:08.024Z · comments (4)
[link] Our Digital and Biological Children
Eneasz · 2024-10-24T18:36:38.719Z · comments (0)
[link] Arithmetic Models: Better Than You Think
kqr · 2024-10-26T09:42:07.185Z · comments (5)
[link] If-Then Commitments for AI Risk Reduction [by Holden Karnofsky]
habryka (habryka4) · 2024-09-13T19:38:53.194Z · comments (0)
[link] Generic advice caveats
Saul Munn (saul-munn) · 2024-10-30T21:03:07.185Z · comments (1)
[link] Predicting Influenza Abundance in Wastewater Metagenomic Sequencing Data
jefftk (jkaufman) · 2024-09-23T17:25:58.380Z · comments (0)
Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs
Daniel Lee (daniel-lee) · 2024-09-06T02:28:41.954Z · comments (0)
An AI crash is our best bet for restricting AI
Remmelt (remmelt-ellen) · 2024-10-11T02:12:03.491Z · comments (3)
Why is there Nothing rather than Something?
Logan Zoellner (logan-zoellner) · 2024-10-26T12:37:50.204Z · comments (3)
Bay Winter Solstice 2024: song leading auditions
tcheasdfjkl · 2024-11-10T23:59:08.199Z · comments (0)
European Progress Conference
Martin Sustrik (sustrik) · 2024-10-06T11:10:03.819Z · comments (11)
Interpretability of SAE Features Representing Check in ChessGPT
Jonathan Kutasov (jonathan-kutasov) · 2024-10-05T20:43:36.679Z · comments (2)
the Daydication technique
chaosmage · 2024-10-18T21:47:46.448Z · comments (0)
Domain-specific SAEs
jacob_drori (jacobcd52) · 2024-10-07T20:15:38.584Z · comments (0)
There aren't enough smart people in biology doing something boring
Abhishaike Mahajan (abhishaike-mahajan) · 2024-10-21T15:52:04.482Z · comments (13)
[question] Any real toeholds for making practical decisions regarding AI safety?
lukehmiles (lcmgcd) · 2024-09-29T12:03:08.084Z · answers+comments (6)
Superintelligence Can't Solve the Problem of Deciding What You'll Do
Vladimir_Nesov · 2024-09-15T21:03:28.077Z · comments (11)
Distinguishing ways AI can be "concentrated"
Matthew Barnett (matthew-barnett) · 2024-10-21T22:21:13.666Z · comments (2)
[question] What prevents SB-1047 from triggering on deep fake porn/voice cloning fraud?
ChristianKl · 2024-09-26T09:17:39.088Z · answers+comments (21)
[link] Evaluating Synthetic Activations composed of SAE Latents in GPT-2
Giorgi Giglemiani (Rakh) · 2024-09-25T20:37:48.227Z · comments (0)
SAEs you can See: Applying Sparse Autoencoders to Clustering
Robert_AIZI · 2024-10-28T14:48:16.744Z · comments (0)
Standard SAEs Might Be Incoherent: A Choosing Problem & A “Concise” Solution
Kola Ayonrinde (kola-ayonrinde) · 2024-10-30T22:50:45.642Z · comments (0)
[link] Care Doesn't Scale
stavros · 2024-10-28T11:57:38.742Z · comments (1)
[link] A brief history of the automated corporation
owencb · 2024-11-04T14:35:04.906Z · comments (1)
Sleeping on Stage
jefftk (jkaufman) · 2024-10-22T00:50:07.994Z · comments (3)
[question] Seeking AI Alignment Tutor/Advisor: $100–150/hr
MrThink (ViktorThink) · 2024-10-05T21:28:16.491Z · answers+comments (3)
← previous page (newer posts) · next page (older posts) →