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) →

EIS XIV: Is mechanistic interpretability about to be practically useful?
scasper · 2024-10-11T22:13:51.033Z · comments (4)
[link] On Shifgrethor
JustisMills · 2024-10-27T15:30:13.688Z · comments (18)
The Third Fundamental Question
Screwtape · 2024-11-15T04:01:33.770Z · comments (7)
Schelling game evaluations for AI control
Olli Järviniemi (jarviniemi) · 2024-10-08T12:01:24.389Z · comments (5)
Occupational Licensing Roundup #1
Zvi · 2024-10-30T11:00:04.516Z · comments (11)
[link] An Opinionated Evals Reading List
Marius Hobbhahn (marius-hobbhahn) · 2024-10-15T14:38:58.778Z · comments (0)
Book Review: On the Edge: The Fundamentals
Zvi · 2024-09-23T13:40:11.058Z · comments (3)
[Intuitive self-models] 8. Rooting Out Free Will Intuitions
Steven Byrnes (steve2152) · 2024-11-04T18:16:26.736Z · comments (16)
AI Craftsmanship
abramdemski · 2024-11-11T22:17:01.112Z · comments (7)
[link] AI, centralization, and the One Ring
owencb · 2024-09-13T14:00:16.126Z · comments (11)
AI research assistants competition 2024Q3: Tie between Elicit and You.com
Elizabeth (pktechgirl) · 2024-10-12T15:10:05.417Z · comments (4)
Another argument against maximizer-centric alignment paradigms
Fiora from Rosebloom · 2024-09-22T07:28:27.856Z · comments (39)
[question] Is cybercrime really costing trillions per year?
Fabien Roger (Fabien) · 2024-09-27T08:44:07.621Z · answers+comments (28)
Perils of Generalizing from One's Social Group
localdeity · 2024-11-24T15:31:18.332Z · comments (1)
[link] Pay-on-results personal growth: first success
Chipmonk · 2024-09-14T03:39:12.975Z · comments (5)
SAEs are highly dataset dependent: a case study on the refusal direction
Connor Kissane (ckkissane) · 2024-11-07T05:22:18.807Z · comments (4)
Book Review: On the Edge: The Future
Zvi · 2024-09-27T14:00:05.279Z · comments (1)
[link] Electrostatic Airships?
DaemonicSigil · 2024-10-27T04:32:34.852Z · comments (13)
[link] on bacteria, on teeth
bhauth · 2024-09-30T15:56:56.830Z · comments (9)
[link] Slightly More Than You Wanted To Know: Pregnancy Length Effects
JustisMills · 2024-10-21T01:26:02.030Z · comments (4)
[Intuitive self-models] 6. Awakening / Enlightenment / PNSE
Steven Byrnes (steve2152) · 2024-10-22T13:23:08.836Z · comments (6)
[link] New o1-like model (QwQ) beats Claude 3.5 Sonnet with only 32B parameters
Jesse Hoogland (jhoogland) · 2024-11-27T22:06:12.914Z · comments (3)
What is SB 1047 *for*?
Raemon · 2024-09-05T17:39:39.871Z · comments (8)
[link] electric turbofans
bhauth · 2024-11-02T22:50:59.807Z · comments (2)
Why imperfect adversarial robustness doesn't doom AI control
Buck · 2024-11-18T16:05:06.763Z · comments (27)
MATS Alumni Impact Analysis
utilistrutil · 2024-09-30T02:35:57.273Z · comments (7)
Against empathy-by-default
Steven Byrnes (steve2152) · 2024-10-16T16:38:49.926Z · comments (24)
Why our politicians aren't Median
Yair Halberstadt (yair-halberstadt) · 2024-11-03T14:03:33.779Z · comments (15)
AI Alignment via Slow Substrates: Early Empirical Results With StarCraft II
Lester Leong (lester-leong) · 2024-10-14T04:05:05.096Z · comments (9)
[link] Dario Amodei — Machines of Loving Grace
Matrice Jacobine · 2024-10-11T21:43:31.448Z · comments (26)
Base LLMs refuse too
Connor Kissane (ckkissane) · 2024-09-29T16:04:21.343Z · comments (20)
Pollsters Should Publish Question Translations
jefftk (jkaufman) · 2024-09-08T22:10:04.932Z · comments (3)
Toward Safety Cases For AI Scheming
Mikita Balesni (mykyta-baliesnyi) · 2024-10-31T17:20:06.019Z · comments (1)
[link] Linkpost: Memorandum on Advancing the United States’ Leadership in Artificial Intelligence
Nisan · 2024-10-25T04:37:00.828Z · comments (2)
AI #81: Alpha Proteo
Zvi · 2024-09-12T13:00:07.958Z · comments (3)
[link] "Map of AI Futures" - An interactive flowchart
swante · 2024-11-27T21:31:40.269Z · comments (3)
Training AI agents to solve hard problems could lead to Scheming
Marius Hobbhahn (marius-hobbhahn) · 2024-11-19T00:10:55.522Z · comments (12)
The Geometry of Feelings and Nonsense in Large Language Models
7vik (satvik-golechha) · 2024-09-27T17:49:27.420Z · comments (10)
[Intuitive self-models] 5. Dissociative Identity (Multiple Personality) Disorder
Steven Byrnes (steve2152) · 2024-10-15T13:31:46.157Z · comments (7)
Mira Murati leaves OpenAI/ OpenAI to remove non-profit control
Sodium · 2024-09-25T21:15:17.315Z · comments (4)
AI #86: Just Think of the Potential
Zvi · 2024-10-17T15:10:06.552Z · comments (8)
How you can help pass important AI legislation with 10 minutes of effort
ThomasW · 2024-09-14T22:10:50.386Z · comments (2)
You should consider applying to PhDs (soon!)
bilalchughtai (beelal) · 2024-11-29T20:33:12.462Z · comments (2)
AI #87: Staying in Character
Zvi · 2024-10-29T07:10:08.212Z · comments (3)
[link] The Alignment Trap: AI Safety as Path to Power
crispweed · 2024-10-29T15:21:26.545Z · comments (17)
[question] Could orcas be (trained to be) smarter than humans? 
Towards_Keeperhood (Simon Skade) · 2024-11-04T23:29:26.677Z · answers+comments (20)
On the UBI Paper
Zvi · 2024-09-03T14:50:08.647Z · comments (6)
Seeking Collaborators
abramdemski · 2024-11-01T17:13:36.162Z · comments (14)
Evidence against Learned Search in a Chess-Playing Neural Network
p.b. · 2024-09-13T11:59:55.634Z · comments (3)
U.S.-China Economic and Security Review Commission pushes Manhattan Project-style AI initiative
Phib · 2024-11-19T18:42:43.296Z · comments (7)
← previous page (newer posts) · next page (older posts) →