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) →

Concrete empirical research projects in mechanistic anomaly detection
Erik Jenner (ejenner) · 2024-04-03T23:07:21.502Z · comments (3)
Debate: Get a college degree?
Ben Pace (Benito) · 2024-08-12T22:23:34.744Z · comments (14)
Protocol evaluations: good analogies vs control
Fabien Roger (Fabien) · 2024-02-19T18:00:09.794Z · comments (10)
[link] Things I learned talking to the new breed of scientific institution
Abhishaike Mahajan (abhishaike-mahajan) · 2024-08-29T14:00:14.844Z · comments (6)
Unit economics of LLM APIs
dschwarz · 2024-08-27T16:51:22.692Z · comments (0)
Deep and obvious points in the gap between your thoughts and your pictures of thought
KatjaGrace · 2024-02-23T07:30:07.461Z · comments (6)
[link] you should probably eat oatmeal sometimes
bhauth · 2024-08-25T14:50:37.570Z · comments (32)
[link] We Need Major, But Not Radical, FDA Reform
Maxwell Tabarrok (maxwell-tabarrok) · 2024-02-24T16:54:33.061Z · comments (12)
How I internalized my achievements to better deal with negative feelings
Raymond Koopmanschap · 2024-02-27T15:10:24.149Z · comments (7)
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)
Formalizing the Informal (event invite)
abramdemski · 2024-09-10T19:22:53.564Z · comments (0)
Housing Roundup #7
Zvi · 2024-03-04T15:00:08.192Z · comments (1)
Paper Summary: The Effects of Communicating Uncertainty on Public Trust in Facts and Numbers
Jeffrey Heninger (jeffrey-heninger) · 2024-07-09T16:50:05.776Z · comments (2)
[link] Surgery Works Well Without The FDA
Maxwell Tabarrok (maxwell-tabarrok) · 2024-01-26T13:31:29.968Z · comments (28)
[link] Soviet comedy film recommendations
Nina Panickssery (NinaR) · 2024-06-09T23:40:58.536Z · comments (11)
Estimating efficiency improvements in LLM pre-training
Daan · 2024-01-19T19:32:45.124Z · comments (3)
[question] What rationality failure modes are there?
Ulisse Mini (ulisse-mini) · 2024-01-19T09:12:57.924Z · answers+comments (11)
Koan: divining alien datastructures from RAM activations
TsviBT · 2024-04-05T18:04:57.280Z · comments (10)
US Presidential Election: Tractability, Importance, and Urgency
kuhanj · 2024-05-29T23:52:22.420Z · comments (2)
Australian AI Safety Forum 2024
Liam Carroll (liam-carroll) · 2024-09-27T00:40:11.451Z · comments (0)
Examining Language Model Performance with Reconstructed Activations using Sparse Autoencoders
Evan Anders (evan-anders) · 2024-02-27T02:43:22.446Z · comments (16)
[link] cold aluminum for medicine
bhauth · 2023-12-16T14:38:03.260Z · comments (4)
[Valence series] 5. “Valence Disorders” in Mental Health & Personality
Steven Byrnes (steve2152) · 2023-12-18T15:26:29.970Z · comments (12)
Trust as a bottleneck to growing teams quickly
benkuhn · 2024-07-13T18:00:04.579Z · comments (3)
Evidential Cooperation in Large Worlds: Potential Objections & FAQ
Chi Nguyen · 2024-02-28T18:58:25.688Z · comments (5)
[link] AI Girlfriends Won't Matter Much
Maxwell Tabarrok (maxwell-tabarrok) · 2023-12-23T15:58:30.308Z · comments (22)
D&D.Sci Alchemy: Archmage Anachronos and the Supply Chain Issues
aphyer · 2024-06-07T19:02:06.859Z · comments (16)
[link] Post series on "Liability Law for reducing Existential Risk from AI"
Nora_Ammann · 2024-02-29T04:39:50.557Z · comments (1)
Take SCIFs, it’s dangerous to go alone
latterframe · 2024-05-01T08:02:38.067Z · comments (1)
Case studies on social-welfare-based standards in various industries
HoldenKarnofsky · 2024-06-20T13:33:44.780Z · comments (0)
[link] Rowing vs steering
Saul Munn (saul-munn) · 2024-08-10T07:00:17.594Z · comments (2)
Wholesomeness and Effective Altruism
owencb · 2024-02-28T20:28:22.175Z · comments (3)
NYT is suing OpenAI&Microsoft for alleged copyright infringement; some quick thoughts
Mikhail Samin (mikhail-samin) · 2023-12-27T18:44:33.976Z · comments (17)
MonoPoly Restricted Trust
ymeskhout · 2024-01-02T23:02:55.066Z · comments (37)
When fine-tuning fails to elicit GPT-3.5's chess abilities
Theodore Chapman · 2024-06-14T18:50:52.855Z · comments (3)
Upgrading the AI Safety Community
trevor (TrevorWiesinger) · 2023-12-16T15:34:26.600Z · comments (9)
Taking responsibility and partial derivatives
Ruby · 2023-12-31T04:33:51.419Z · comments (1)
Startup Success Rates Are So Low Because the Rewards Are So Large
AppliedDivinityStudies (kohaku-none) · 2024-10-10T20:22:01.557Z · comments (6)
Time Efficient Resistance Training
romeostevensit · 2024-10-07T15:15:44.950Z · comments (10)
AI #89: Trump Card
Zvi · 2024-11-07T16:30:05.684Z · comments (12)
MATS AI Safety Strategy Curriculum v2
DanielFilan · 2024-10-07T22:44:06.396Z · comments (6)
Reflections on the Metastrategies Workshop
gw · 2024-10-24T18:30:46.255Z · comments (5)
[link] IAPS: Mapping Technical Safety Research at AI Companies
Zach Stein-Perlman · 2024-10-24T20:30:41.159Z · comments (12)
D&D Sci Coliseum: Arena of Data
aphyer · 2024-10-18T22:02:54.305Z · comments (23)
[link] Point of Failure: Semiconductor-Grade Quartz
Annapurna (jorge-velez) · 2024-09-30T15:57:40.495Z · comments (8)
Notes on Dwarkesh Patel’s Podcast with Sholto Douglas and Trenton Bricken
Zvi · 2024-04-01T19:10:12.193Z · comments (1)
[link] What's new at FAR AI
AdamGleave · 2023-12-04T21:18:03.951Z · comments (0)
[link] Podcast with Yoshua Bengio on Why AI Labs are “Playing Dice with Humanity’s Future”
garrison · 2024-05-10T17:23:20.436Z · comments (0)
AI Risk and the US Presidential Candidates
Zane · 2024-01-06T20:18:04.945Z · comments (22)
On plans for a functional society
kave · 2023-12-12T00:07:46.629Z · comments (8)
← previous page (newer posts) · next page (older posts) →