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) →

Self location for LLMs by LLMs: Self-Assessment Checklist.
weightt an (weightt-an) · 2024-09-26T19:57:31.707Z · comments (0)
What You Can Give Instead of Advice
Karl Faulks (karl-faulks) · 2024-10-24T23:10:48.014Z · comments (2)
[link] AI Safety Newsletter #40: California AI Legislation Plus, NVIDIA Delays Chip Production, and Do AI Safety Benchmarks Actually Measure Safety?
Corin Katzke (corin-katzke) · 2024-08-21T18:09:33.284Z · comments (0)
What is Randomness?
martinkunev · 2024-09-27T17:49:42.704Z · comments (2)
[link] OpenAI’s cybersecurity is probably regulated by NIS Regulations
Adam Jones (domdomegg) · 2024-10-25T11:06:38.392Z · comments (2)
A Poem Is All You Need: Jailbreaking ChatGPT, Meta & More
Sharat Jacob Jacob (sharat-jacob-jacob) · 2024-10-29T12:41:30.337Z · comments (0)
The Other Existential Crisis
James Stephen Brown (james-brown) · 2024-09-21T01:16:38.011Z · comments (24)
[question] How Should We Use Limited Time to Maximize Long-Term Impact?
queelius · 2024-10-12T20:02:46.801Z · answers+comments (3)
[question] LW resources on childhood experiences?
nahir91595 · 2024-10-14T17:04:07.810Z · answers+comments (7)
[link] HVM Superposition Node Program Search Flake
Johannes C. Mayer (johannes-c-mayer) · 2024-08-09T14:03:16.381Z · comments (0)
[question] Does life actually locally *increase* entropy?
tailcalled · 2024-09-16T20:30:33.148Z · answers+comments (27)
[Job Ad] MATS is hiring!
Jana (jana) · 2024-10-09T02:17:04.651Z · comments (0)
Request for advice: Research for Conversational Game Theory for LLMs
Rome Viharo (rome-viharo) · 2024-10-16T17:53:30.243Z · comments (0)
[question] What's a good book for a technically-minded 11-year old?
Martin Sustrik (sustrik) · 2024-10-19T06:05:12.178Z · answers+comments (27)
[link] How harmful is music, really?
dkl9 · 2024-09-17T14:53:25.426Z · comments (6)
Keyboard Gremlins
jefftk (jkaufman) · 2024-09-20T02:30:07.140Z · comments (0)
[link] When to join a respectability cascade
B Jacobs (Bob Jacobs) · 2024-09-24T07:54:16.051Z · comments (1)
Pleasure and suffering are not conceptual opposites
MichaelStJules · 2024-08-11T18:32:30.359Z · comments (0)
On agentic generalist models: we're essentially using existing technology the weakest and worst way you can use it
Yuli_Ban · 2024-08-28T01:57:17.387Z · comments (2)
Crafting Polysemantic Transformer Benchmarks with Known Circuits
Evan Anders (evan-anders) · 2024-08-23T22:03:15.288Z · comments (0)
Just How Good Are Modern Chess Computers?
nem · 2024-09-19T18:57:21.254Z · comments (1)
[question] Where should I look for information on gut health?
FinalFormal2 · 2024-08-20T19:44:30.632Z · answers+comments (10)
Lenses of Control
WillPetillo · 2024-10-22T07:51:06.355Z · comments (0)
[question] I want a good multi-LLM API-powered chatbot
rotatingpaguro · 2024-09-08T09:40:52.736Z · answers+comments (3)
Making a Pedalboard
jefftk (jkaufman) · 2024-10-25T00:10:09.149Z · comments (0)
A Policy Proposal
phdead · 2024-09-29T20:45:34.745Z · comments (4)
[link] Molecular dynamics data will be essential for the next generation of ML protein models
Abhishaike Mahajan (abhishaike-mahajan) · 2024-08-26T14:50:23.790Z · comments (0)
[link] Virtue is a Vector
robotelvis · 2024-09-10T03:02:45.737Z · comments (1)
[link] The EA case for Trump
Judd Rosenblatt (judd) · 2024-08-03T01:00:45.422Z · comments (1)
[link] Apply to Aether - Independent LLM Agent Safety Research Group
RohanS · 2024-08-21T09:47:11.493Z · comments (0)
[question] What do you expect AI capabilities may look like in 2028?
nonzerosum · 2024-08-23T16:59:53.007Z · answers+comments (5)
Derivative AT a discontinuity
Alok Singh (OldManNick) · 2024-10-24T02:48:24.573Z · comments (2)
A Dialogue on Deceptive Alignment Risks
Rauno Arike (rauno-arike) · 2024-09-25T16:10:12.294Z · comments (0)
[link] In Praise of the Beatitudes
robotelvis · 2024-09-24T05:08:21.133Z · comments (7)
Rationalist Gnosticism
tailcalled · 2024-10-10T09:06:34.149Z · comments (10)
Simultaneous Footbass and Footdrums II
jefftk (jkaufman) · 2024-08-11T23:50:01.982Z · comments (0)
[question] What are some of the proposals for solving the control problem?
Dakara (chess-ice) · 2024-08-14T23:04:44.863Z · answers+comments (0)
Open letter to young EAs
Leif Wenar · 2024-10-11T19:49:10.818Z · comments (10)
[link] Why do firms choose to be inefficient?
Nicholas D. (nicholas-d) · 2024-08-28T18:39:41.664Z · comments (4)
[question] Is this a Pivotal Weak Act? Creating bacteria that decompose metal
doomyeser · 2024-09-11T18:07:19.385Z · answers+comments (9)
[link] Physics of Language models (part 2.1)
Nathan Helm-Burger (nathan-helm-burger) · 2024-09-19T16:48:32.301Z · comments (2)
[link] Temporary Cognitive Hyperparameter Alteration
Jonathan Moregård (JonathanMoregard) · 2024-08-01T10:27:11.917Z · comments (0)
Keeping it (less than) real: Against ℶ₂ possible people or worlds
quiet_NaN · 2024-09-13T17:29:44.915Z · comments (0)
[question] Doing Nothing Utility Function
k64 · 2024-09-26T22:05:18.821Z · answers+comments (9)
[link] Testing Genetic Engineering Detection with Spike-Ins
jefftk (jkaufman) · 2024-10-22T17:20:54.947Z · comments (0)
[question] Are UV-C Air purifiers so useful?
JohnBuridan · 2024-09-04T14:16:01.310Z · answers+comments (0)
Will AI and Humanity Go to War?
Simon Goldstein (simon-goldstein) · 2024-10-01T06:35:22.374Z · comments (4)
Thinking About a Pedalboard
jefftk (jkaufman) · 2024-10-08T11:50:02.054Z · comments (2)
AGI's Opposing Force
SimonBaars (simonbaars) · 2024-08-16T04:18:06.900Z · comments (2)
how to rapidly assimilate new information
dhruvmethi · 2024-10-24T02:18:00.648Z · comments (3)
← previous page (newer posts) · next page (older posts) →