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) →

Conflating value alignment and intent alignment is causing confusion
Seth Herd · 2024-09-05T16:39:51.967Z · comments (18)
Untrustworthy models: a frame for scheming evaluations
Olli Järviniemi (jarviniemi) · 2024-08-19T16:27:11.088Z · comments (3)
[link] MIRI's September 2024 newsletter
Harlan · 2024-09-16T18:15:40.785Z · comments (0)
All The Latest Human tFUS Studies
sarahconstantin · 2024-08-09T22:20:04.561Z · comments (2)
Decision Theory in Space
lsusr · 2024-08-18T07:02:11.847Z · comments (18)
Bounty for Evidence on Some of Palisade Research's Beliefs
benwr · 2024-09-23T20:01:20.917Z · comments (4)
D&D.Sci Coliseum: Arena of Data Evaluation and Ruleset
aphyer · 2024-10-29T01:21:03.075Z · comments (10)
How might we solve the alignment problem? (Part 1: Intro, summary, ontology)
Joe Carlsmith (joekc) · 2024-10-28T21:57:12.063Z · comments (5)
How to hire somebody better than yourself
lukehmiles (lcmgcd) · 2024-08-28T08:12:53.450Z · comments (5)
AI #80: Never Have I Ever
Zvi · 2024-09-10T17:50:08.074Z · comments (20)
Startup Roundup #2
Zvi · 2024-08-06T13:30:06.554Z · comments (0)
Work with me on agent foundations: independent fellowship
Alex_Altair · 2024-09-21T13:59:16.706Z · comments (5)
Principled Satisficing To Avoid Goodhart
JenniferRM · 2024-08-16T19:05:27.204Z · comments (2)
~80 Interesting Questions about Foundation Model Agent Safety
RohanS · 2024-10-28T16:37:04.713Z · comments (4)
We Don't Know Our Own Values, but Reward Bridges The Is-Ought Gap
johnswentworth · 2024-09-19T22:22:05.307Z · comments (47)
[question] "Deception Genre" What Books are like Project Lawful?
Double · 2024-08-28T17:19:52.172Z · answers+comments (20)
Start an Upper-Room UV Installation Company?
jefftk (jkaufman) · 2024-10-19T02:00:10.691Z · comments (9)
Economics Roundup #3
Zvi · 2024-09-10T13:50:06.955Z · comments (9)
In defense of technological unemployment as the main AI concern
tailcalled · 2024-08-27T17:58:01.992Z · comments (36)
Occupational Licensing Roundup #1
Zvi · 2024-10-30T11:00:04.516Z · comments (7)
How difficult is AI Alignment?
Sammy Martin (SDM) · 2024-09-13T15:47:10.799Z · comments (6)
Minimal Motivation of Natural Latents
johnswentworth · 2024-10-14T22:51:58.125Z · comments (14)
[link] cancer rates after gene therapy
bhauth · 2024-10-16T15:32:53.949Z · comments (0)
Which LessWrong/Alignment topics would you like to be tutored in? [Poll]
Ruby · 2024-09-19T01:35:02.999Z · comments (12)
Debate: Get a college degree?
Ben Pace (Benito) · 2024-08-12T22:23:34.744Z · comments (14)
A Robust Natural Latent Over A Mixed Distribution Is Natural Over The Distributions Which Were Mixed
johnswentworth · 2024-08-22T19:19:28.940Z · comments (4)
[link] Rowing vs steering
Saul Munn (saul-munn) · 2024-08-10T07:00:17.594Z · comments (2)
Time Efficient Resistance Training
romeostevensit · 2024-10-07T15:15:44.950Z · comments (8)
[link] An Interactive Shapley Value Explainer
James Stephen Brown (james-brown) · 2024-09-28T05:01:21.169Z · comments (9)
Unit economics of LLM APIs
dschwarz · 2024-08-27T16:51:22.692Z · comments (0)
MATS AI Safety Strategy Curriculum v2
DanielFilan · 2024-10-07T22:44:06.396Z · comments (6)
[link] you should probably eat oatmeal sometimes
bhauth · 2024-08-25T14:50:37.570Z · comments (31)
Formalizing the Informal (event invite)
abramdemski · 2024-09-10T19:22:53.564Z · comments (0)
[link] What's important in "AI for epistemics"?
Lukas Finnveden (Lanrian) · 2024-08-24T01:27:06.771Z · comments (0)
Superintelligent AI is possible in the 2020s
HunterJay · 2024-08-13T06:03:26.990Z · comments (3)
[link] Point of Failure: Semiconductor-Grade Quartz
Annapurna (jorge-velez) · 2024-09-30T15:57:40.495Z · comments (8)
[link] [Paper] Programming Refusal with Conditional Activation Steering
Bruce W. Lee (bruce-lee) · 2024-09-11T20:57:08.714Z · comments (0)
[link] Things I learned talking to the new breed of scientific institution
Abhishaike Mahajan (abhishaike-mahajan) · 2024-08-29T14:00:14.844Z · comments (6)
[link] Adverse Selection by Life-Saving Charities
vaishnav92 · 2024-08-14T20:46:23.662Z · comments (16)
Startup Success Rates Are So Low Because the Rewards Are So Large
AppliedDivinityStudies (kohaku-none) · 2024-10-10T20:22:01.557Z · comments (6)
instruction tuning and autoregressive distribution shift
nostalgebraist · 2024-09-05T16:53:41.497Z · comments (5)
Californians, tell your reps to vote yes on SB 1047!
Holly_Elmore · 2024-08-12T19:50:09.817Z · comments (24)
[Linkpost] Play with SAEs on Llama 3
Tom McGrath · 2024-09-25T22:35:44.824Z · comments (2)
D&D Sci Coliseum: Arena of Data
aphyer · 2024-10-18T22:02:54.305Z · comments (22)
Why did ChatGPT say that? Prompt engineering and more, with PIZZA.
Jessica Rumbelow (jessica-cooper) · 2024-08-03T12:07:46.302Z · comments (2)
Monthly Roundup #23: October 2024
Zvi · 2024-10-16T13:50:05.869Z · comments (12)
Reflections on the Metastrategies Workshop
gw · 2024-10-24T18:30:46.255Z · comments (5)
2025 Color Trends
sarahconstantin · 2024-10-07T21:20:03.962Z · comments (7)
[question] Implications of China's recession on AGI development?
Eric Neyman (UnexpectedValues) · 2024-09-28T01:12:36.443Z · answers+comments (3)
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
Kola Ayonrinde (kola-ayonrinde) · 2024-08-23T18:52:31.019Z · comments (5)
← previous page (newer posts) · next page (older posts) →