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) →

A Visual Task that's Hard for GPT-4o, but Doable for Primary Schoolers
Lennart Finke (l-f) · 2024-07-26T17:51:28.202Z · comments (4)
Decent plan prize announcement (1 paragraph, $1k)
lukehmiles (lcmgcd) · 2024-01-12T06:27:44.495Z · comments (19)
Twin Peaks: under the air
KatjaGrace · 2024-05-31T01:20:04.624Z · comments (2)
[link] Beware the science fiction bias in predictions of the future
Nikita Sokolsky (nikita-sokolsky) · 2024-08-19T05:32:47.372Z · comments (20)
[link] The Best Essay (Paul Graham)
Chris_Leong · 2024-03-11T19:25:42.176Z · comments (2)
Beta Tester Request: Rallypoint Bounties
lukemarks (marc/er) · 2024-05-25T09:11:11.446Z · comments (4)
[link] MIRI's July 2024 newsletter
Harlan · 2024-07-15T21:28:17.343Z · comments (2)
[link] Executive Dysfunction 101
DaystarEld · 2024-05-23T12:43:13.785Z · comments (1)
[link] Transformer Debugger
Henk Tillman (henk-tillman) · 2024-03-12T19:08:56.280Z · comments (0)
[link] what becoming more secure did for me
Chipmonk · 2024-08-22T17:44:48.525Z · comments (5)
Using an LLM perplexity filter to detect weight exfiltration
Adam Karvonen (karvonenadam) · 2024-07-21T18:18:05.612Z · comments (11)
Housing Roundup #9: Restricting Supply
Zvi · 2024-07-17T12:50:05.321Z · comments (8)
Useful starting code for interpretability
eggsyntax · 2024-02-13T23:13:47.940Z · comments (2)
Building Trust in Strategic Settings
StrivingForLegibility · 2023-12-28T22:12:24.024Z · comments (0)
Scientific Method
Andrij “Androniq” Ghorbunov (andrij-androniq-ghorbunov) · 2024-02-18T21:06:45.228Z · comments (4)
[link] Clickbait Soapboxing
DaystarEld · 2024-03-13T14:09:29.890Z · comments (15)
I didn't think I'd take the time to build this calibration training game, but with websim it took roughly 30 seconds, so here it is!
mako yass (MakoYass) · 2024-08-02T22:35:21.136Z · comments (2)
[link] The absence of self-rejection is self-acceptance
Chipmonk · 2023-12-21T21:54:52.116Z · comments (1)
[link] Was Partisanship Good for the Environmental Movement?
Jeffrey Heninger (jeffrey-heninger) · 2024-05-15T17:30:54.796Z · comments (0)
Population ethics and the value of variety
cousin_it · 2024-06-23T10:42:21.402Z · comments (11)
[link] Secret US natsec project with intel revealed
Nathan Helm-Burger (nathan-helm-burger) · 2024-05-25T04:22:11.624Z · comments (0)
Language and Capabilities: Testing LLM Mathematical Abilities Across Languages
Ethan Edwards · 2024-04-04T13:18:54.909Z · comments (2)
[link] Altruism and Vitalism Aren't Fellow Travelers
Arjun Panickssery (arjun-panickssery) · 2024-08-09T02:01:11.361Z · comments (2)
Best-of-n with misaligned reward models for Math reasoning
Fabien Roger (Fabien) · 2024-06-21T22:53:21.243Z · comments (0)
[link] Robert Caro And Mechanistic Models In Biography
adamShimi · 2024-07-14T10:56:42.763Z · comments (5)
Technology path dependence and evaluating expertise
bhauth · 2024-01-05T19:21:23.302Z · comments (2)
[link] Alignment work in anomalous worlds
Tamsin Leake (carado-1) · 2023-12-16T19:34:26.202Z · comments (4)
[link] Compensating for Life Biases
Jonathan Moregård (JonathanMoregard) · 2024-01-09T14:39:14.229Z · comments (6)
Trying to be rational for the wrong reasons
Viliam · 2024-08-20T16:18:06.385Z · comments (8)
[link] Truth is Universal: Robust Detection of Lies in LLMs
Lennart Buerger · 2024-07-19T14:07:25.162Z · comments (3)
A brief review of China's AI industry and regulations
Elliot Mckernon (elliot) · 2024-03-14T12:19:00.775Z · comments (0)
UDT1.01: Local Affineness and Influence Measures (2/10)
Diffractor · 2024-03-31T07:35:52.831Z · comments (0)
[link] Let's Design A School, Part 2.3 School as Education - The Curriculum (Phase 2, Specific)
Sable · 2024-05-15T20:58:50.981Z · comments (0)
[link] The Living Planet Index: A Case Study in Statistical Pitfalls
Jan_Kulveit · 2024-06-24T10:05:55.101Z · comments (0)
[link] Scenario planning for AI x-risk
Corin Katzke (corin-katzke) · 2024-02-10T00:14:11.934Z · comments (12)
Paper Summary: The Koha Code - A Biological Theory of Memory
jakej (jake-jenks) · 2023-12-30T22:37:13.865Z · comments (2)
Even if we lose, we win
Morphism (pi-rogers) · 2024-01-15T02:15:43.447Z · comments (17)
Foresight Institute: 2023 Progress & 2024 Plans for funding beneficial technology development
Allison Duettmann (allison-duettmann) · 2023-11-22T22:09:16.956Z · comments (1)
A bet on critical periods in neural networks
kave · 2023-11-06T23:21:17.279Z · comments (1)
[link] Cellular respiration as a steam engine
dkl9 · 2024-02-25T20:17:38.788Z · comments (1)
An evaluation of Helen Toner’s interview on the TED AI Show
PeterH · 2024-06-06T17:39:40.800Z · comments (2)
aintelope project update
Gunnar_Zarncke · 2024-02-08T18:32:00.000Z · comments (2)
How Congressional Offices Process Constituent Communication
Tristan Williams (tristan-williams) · 2024-07-02T12:38:41.472Z · comments (0)
My Alignment "Plan": Avoid Strong Optimisation and Align Economy
VojtaKovarik · 2024-01-31T17:03:34.778Z · comments (9)
[question] Would you have a baby in 2024?
martinkunev · 2023-12-25T01:52:04.358Z · answers+comments (76)
Distinctions when Discussing Utility Functions
ozziegooen · 2024-03-09T20:14:03.592Z · comments (7)
[link] Eric Schmidt on recursive self-improvement
nikola (nikolaisalreadytaken) · 2023-11-05T19:05:15.416Z · comments (3)
[link] Extinction Risks from AI: Invisible to Science?
VojtaKovarik · 2024-02-21T18:07:33.986Z · comments (7)
Evolution did a surprising good job at aligning humans...to social status
Eli Tyre (elityre) · 2024-03-10T19:34:52.544Z · comments (37)
Utility is not the selection target
tailcalled · 2023-11-04T22:48:20.713Z · comments (1)
← previous page (newer posts) · next page (older posts) →