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] Recommendations for Technical AI Safety Research Directions
Sam Marks (samuel-marks) · 2025-01-10T19:34:04.920Z · comments (1)
[link] Gaming TruthfulQA: Simple Heuristics Exposed Dataset Weaknesses
TurnTrout · 2025-01-16T02:14:35.098Z · comments (3)
AI Craftsmanship
abramdemski · 2024-11-11T22:17:01.112Z · comments (7)
Retrospective: PIBBSS Fellowship 2024
DusanDNesic · 2024-12-20T15:55:24.194Z · comments (1)
An Illustrated Summary of "Robust Agents Learn Causal World Model"
Dalcy (Darcy) · 2024-12-14T15:02:44.828Z · comments (2)
Neuroscience of human social instincts: a sketch
Steven Byrnes (steve2152) · 2024-11-22T16:16:52.552Z · comments (0)
[link] RL, but don't do anything I wouldn't do
Gunnar_Zarncke · 2024-12-07T22:54:50.714Z · comments (5)
Perils of Generalizing from One's Social Group
localdeity · 2024-11-24T15:31:18.332Z · comments (1)
Why our politicians aren't Median
Yair Halberstadt (yair-halberstadt) · 2024-11-03T14:03:33.779Z · comments (15)
[link] Zen and The Art of Semiconductor Manufacturing
Recurrented (rachel-farley) · 2024-12-09T17:19:35.236Z · comments (2)
[link] Slightly More Than You Wanted To Know: Pregnancy Length Effects
JustisMills · 2024-10-21T01:26:02.030Z · comments (4)
[link] "We know how to build AGI" - Sam Altman
Nikola Jurkovic (nikolaisalreadytaken) · 2025-01-06T02:05:05.134Z · comments (5)
[Intuitive self-models] 6. Awakening / Enlightenment / PNSE
Steven Byrnes (steve2152) · 2024-10-22T13:23:08.836Z · comments (8)
[link] Electrostatic Airships?
DaemonicSigil · 2024-10-27T04:32:34.852Z · comments (13)
ReSolsticed vol I: "We're Not Going Quietly"
Raemon · 2024-12-26T17:52:33.727Z · comments (4)
[link] electric turbofans
bhauth · 2024-11-02T22:50:59.807Z · comments (2)
Cognitive Work and AI Safety: A Thermodynamic Perspective
Daniel Murfet (dmurfet) · 2024-12-08T21:42:17.023Z · comments (9)
Training AI agents to solve hard problems could lead to Scheming
Marius Hobbhahn (marius-hobbhahn) · 2024-11-19T00:10:55.522Z · comments (12)
Why imperfect adversarial robustness doesn't doom AI control
Buck · 2024-11-18T16:05:06.763Z · comments (25)
Checking in on Scott's composition image bet with imagen 3
Dave Orr (dave-orr) · 2024-12-22T19:04:17.495Z · comments (0)
A case for donating to AI risk reduction (including if you work in AI)
tlevin (trevor) · 2024-12-02T19:05:06.658Z · comments (2)
o3, Oh My
Zvi · 2024-12-30T14:10:05.144Z · comments (17)
[link] Linkpost: Memorandum on Advancing the United States’ Leadership in Artificial Intelligence
Nisan · 2024-10-25T04:37:00.828Z · comments (2)
[link] Funding Case: AI Safety Camp 11
Remmelt (remmelt-ellen) · 2024-12-23T08:51:55.255Z · comments (4)
Tips and Code for Empirical Research Workflows
John Hughes (john-hughes) · 2025-01-20T22:31:51.498Z · comments (6)
Retrospective: 12 [sic] Months Since MIRI
james.lucassen · 2025-01-21T02:52:06.271Z · comments (0)
Toward Safety Cases For AI Scheming
Mikita Balesni (mykyta-baliesnyi) · 2024-10-31T17:20:06.019Z · comments (1)
Measuring whether AIs can statelessly strategize to subvert security measures
Alex Mallen (alex-mallen) · 2024-12-19T21:25:28.555Z · comments (0)
Read The Sequences As If They Were Written Today
Peter Berggren (peter-berggren) · 2025-01-02T02:51:36.537Z · comments (7)
o1 Turns Pro
Zvi · 2024-12-10T17:00:08.036Z · comments (3)
[link] Testing for Scheming with Model Deletion
Guive (GAA) · 2025-01-07T01:54:13.550Z · comments (20)
[link] new chinese stealth aircraft
bhauth · 2025-01-01T00:19:10.644Z · comments (3)
[question] Could orcas be (trained to be) smarter than humans? 
Towards_Keeperhood (Simon Skade) · 2024-11-04T23:29:26.677Z · answers+comments (22)
Reading RFK Jr so that you don’t have to
braces · 2024-11-22T00:59:19.583Z · comments (1)
AI #95: o1 Joins the API
Zvi · 2024-12-19T15:10:05.196Z · comments (1)
AI #96: o3 But Not Yet For Thee
Zvi · 2024-12-26T20:30:06.722Z · comments (8)
AI #86: Just Think of the Potential
Zvi · 2024-10-17T15:10:06.552Z · comments (8)
Timaeus is hiring researchers & engineers
Jesse Hoogland (jhoogland) · 2025-01-17T19:13:14.739Z · comments (2)
Seeking Collaborators
abramdemski · 2024-11-01T17:13:36.162Z · comments (15)
[link] The Alignment Trap: AI Safety as Path to Power
crispweed · 2024-10-29T15:21:26.545Z · comments (17)
AI #87: Staying in Character
Zvi · 2024-10-29T07:10:08.212Z · comments (3)
AI #99: Farewell to Biden
Zvi · 2025-01-16T14:20:05.768Z · comments (5)
U.S.-China Economic and Security Review Commission pushes Manhattan Project-style AI initiative
Phib · 2024-11-19T18:42:43.296Z · comments (7)
[link] Ideas for benchmarking LLM creativity
gwern · 2024-12-16T05:18:55.631Z · comments (11)
Win/continue/lose scenarios and execute/replace/audit protocols
Buck · 2024-11-15T15:47:24.868Z · comments (2)
[link] a space habitat design
bhauth · 2024-11-25T17:28:48.481Z · comments (13)
Some lessons from the OpenAI-FrontierMath debacle
7vik (satvik-golechha) · 2025-01-19T21:09:17.990Z · comments (9)
Toward Safety Case Inspired Basic Research
Lucas Teixeira · 2024-10-31T23:06:32.854Z · comments (3)
Vegans need to eat just enough Meat - emperically evaluate the minimum ammount of meat that maximizes utility
Johannes C. Mayer (johannes-c-mayer) · 2024-12-22T22:08:31.971Z · comments (35)
AI Assistants Should Have a Direct Line to Their Developers
Jan_Kulveit · 2024-12-28T17:01:58.643Z · comments (6)
← previous page (newer posts) · next page (older posts) →