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) →

I Finally Worked Through Bayes' Theorem (Personal Achievement)
keltan · 2024-12-05T02:04:16.547Z · comments (6)
What's Behind the SynBio Bust?
sarahconstantin · 2025-01-30T22:30:06.916Z · comments (7)
Against blanket arguments against interpretability
Dmitry Vaintrob (dmitry-vaintrob) · 2025-01-22T09:46:23.486Z · comments (4)
AI #100: Meet the New Boss
Zvi · 2025-01-23T15:40:07.473Z · comments (4)
[link] Epistemic status: poetry (and other poems)
Richard_Ngo (ricraz) · 2024-11-21T18:13:17.194Z · comments (5)
A Solution for AGI/ASI Safety
Weibing Wang (weibing-wang) · 2024-12-18T19:44:29.739Z · comments (29)
Logits, log-odds, and loss for parallel circuits
Dmitry Vaintrob (dmitry-vaintrob) · 2025-01-20T09:56:26.031Z · comments (3)
On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback
Marcus Williams · 2024-11-07T15:39:06.854Z · comments (6)
Role embeddings: making authorship more salient to LLMs
Nina Panickssery (NinaR) · 2025-01-07T20:13:16.677Z · comments (0)
DeekSeek v3: The Six Million Dollar Model
Zvi · 2024-12-31T15:10:06.924Z · comments (6)
[link] A toy evaluation of inference code tampering
Fabien Roger (Fabien) · 2024-12-09T17:43:40.910Z · comments (0)
[link] Careless thinking: A theory of bad thinking
Nathan Young · 2024-12-17T18:23:16.140Z · comments (17)
[link] A dataset of questions on decision-theoretic reasoning in Newcomb-like problems
Caspar Oesterheld (Caspar42) · 2024-12-16T22:42:03.763Z · comments (1)
AI #94: Not Now, Google
Zvi · 2024-12-12T15:40:06.336Z · comments (3)
D&D.Sci Dungeonbuilding: the Dungeon Tournament
aphyer · 2024-12-14T04:30:55.656Z · comments (16)
Analysis of Global AI Governance Strategies
Sammy Martin (SDM) · 2024-12-04T10:45:25.311Z · comments (10)
Dave Kasten's AGI-by-2027 vignette
davekasten · 2024-11-26T23:20:47.212Z · comments (8)
[link] Active Recall and Spaced Repetition are Different Things
Saul Munn (saul-munn) · 2024-11-08T20:14:56.092Z · comments (2)
Greedy-Advantage-Aware RLHF
sej2020 · 2024-12-27T19:47:25.562Z · comments (15)
Cognitive Biases Contributing to AI X-risk — a deleted excerpt from my 2018 ARCHES draft
Andrew_Critch · 2024-12-03T09:29:49.745Z · comments (2)
Finding Features Causally Upstream of Refusal
Daniel Lee (daniel-lee) · 2025-01-14T02:30:04.321Z · comments (5)
Considerations on orca intelligence
Towards_Keeperhood (Simon Skade) · 2024-12-29T14:35:16.445Z · comments (5)
Looking back on the Future of Humanity Institute - Asterisk
jakeeaton · 2024-11-19T00:44:40.928Z · comments (0)
[link] Two interviews with the founder of DeepSeek
Cosmia_Nebula · 2024-11-29T03:18:47.246Z · comments (4)
[link] What Ketamine Therapy Is Like
Sable · 2024-11-11T11:09:08.602Z · comments (8)
[link] Review: Breaking Free with Dr. Stone
TurnTrout · 2024-12-18T01:26:37.730Z · comments (5)
Meta Pivots on Content Moderation
Zvi · 2025-01-17T14:20:06.727Z · comments (3)
[link] Analyzing how SAE features evolve across a forward pass
bensenberner · 2024-11-07T22:07:02.827Z · comments (0)
AI #91: Deep Thinking
Zvi · 2024-11-21T14:30:06.930Z · comments (11)
[link] How quickly could robots scale up?
Benjamin_Todd · 2025-01-12T17:01:04.927Z · comments (22)
Book a Time to Chat about Interp Research
Logan Riggs (elriggs) · 2024-12-03T17:27:46.808Z · comments (3)
AI #97: 4
Zvi · 2025-01-02T14:10:06.505Z · comments (4)
Implications of the AI Security Gap
Dan Braun (dan-braun-1) · 2025-01-08T08:31:36.789Z · comments (0)
DeepSeek: Don’t Panic
Zvi · 2025-01-31T14:20:08.264Z · comments (6)
Things I have been using LLMs for
Kaj_Sotala · 2025-01-20T14:20:02.600Z · comments (5)
[link] The Deep Lore of LightHaven, with Oliver Habryka (TBC episode 228)
Eneasz · 2024-12-24T22:45:50.065Z · comments (4)
[link] Oppression and production are competing explanations for wealth inequality.
Benquo · 2025-01-05T14:13:15.398Z · comments (15)
Detection of Asymptomatically Spreading Pathogens
jefftk (jkaufman) · 2024-12-05T18:20:02.473Z · comments (7)
[link] The Choice Transition
owencb · 2024-11-18T12:30:56.198Z · comments (4)
Escape from Alderaan I
lsusr · 2025-02-02T10:48:06.533Z · comments (2)
On Dwarkesh Patel’s 4th Podcast With Tyler Cowen
Zvi · 2025-01-10T13:50:05.563Z · comments (7)
[link] Literacy Rates Haven't Fallen By 20% Since the Department of Education Was Created
Maxwell Tabarrok (maxwell-tabarrok) · 2024-11-22T20:53:59.007Z · comments (0)
[link] Dangerous capability tests should be harder
LucaRighetti (Error404Dinosaur) · 2024-11-21T17:20:50.610Z · comments (3)
[link] Conjecture: A Roadmap for Cognitive Software and A Humanist Future of AI
Connor Leahy (NPCollapse) · 2024-12-02T13:28:57.977Z · comments (10)
Monthly Roundup #24: November 2024
Zvi · 2024-11-18T13:20:06.086Z · comments (14)
Preppers Are Too Negative on Objects
jefftk (jkaufman) · 2024-12-18T02:30:01.854Z · comments (2)
Zvi’s 2024 In Movies
Zvi · 2025-01-13T13:40:05.488Z · comments (4)
[link] Began a pay-on-results coaching experiment, made $40,300 since July
Chipmonk · 2024-12-29T21:12:02.574Z · comments (15)
Practicing Bayesian Epistemology with "Two Boys" Probability Puzzles
Liron · 2025-01-02T04:42:20.362Z · comments (14)
Dmitry's Koan
Dmitry Vaintrob (dmitry-vaintrob) · 2025-01-10T04:27:30.346Z · comments (8)
← previous page (newer posts) · next page (older posts) →