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) →

On Lex Fridman’s Second Podcast with Altman
Zvi · 2024-03-25T12:20:08.780Z · comments (10)
D&D.Sci Alchemy: Archmage Anachronos and the Supply Chain Issues Evaluation & Ruleset
aphyer · 2024-06-17T21:29:08.778Z · comments (11)
Rewilding the Gut VS the Autoimmune Epidemic
GGD · 2024-08-16T18:00:46.239Z · comments (0)
Applying refusal-vector ablation to a Llama 3 70B agent
Simon Lermen (dalasnoin) · 2024-05-11T00:08:08.117Z · comments (14)
Claude Sonnet 3.5.1 and Haiku 3.5
Zvi · 2024-10-24T14:50:06.286Z · comments (9)
[link] The Good Balsamic Vinegar
jenn (pixx) · 2024-01-26T19:30:57.435Z · comments (4)
So you want to work on technical AI safety
gw · 2024-06-24T14:29:57.481Z · comments (3)
Model evals for dangerous capabilities
Zach Stein-Perlman · 2024-09-23T11:00:00.866Z · comments (11)
[link] Anthropic's updated Responsible Scaling Policy
Zac Hatfield-Dodds (zac-hatfield-dodds) · 2024-10-15T16:46:48.727Z · comments (3)
Does literacy remove your ability to be a bard as good as Homer?
Adrià Garriga-alonso (rhaps0dy) · 2024-01-18T03:43:14.994Z · comments (19)
I Finally Worked Through Bayes' Theorem (Personal Achievement)
keltan · 2024-12-05T02:04:16.547Z · comments (6)
[link] Just one more exposure bro
Chipmonk · 2024-12-12T21:37:07.069Z · comments (6)
Which evals resources would be good?
Marius Hobbhahn (marius-hobbhahn) · 2024-11-16T14:24:48.012Z · comments (4)
Llama Llama-3-405B?
Zvi · 2024-07-24T19:40:07.565Z · comments (9)
Metastatic Cancer Treatment Since 2010: The Success Stories
sarahconstantin · 2024-11-04T22:50:09.386Z · comments (2)
Toy models of AI control for concentrated catastrophe prevention
Fabien Roger (Fabien) · 2024-02-06T01:38:19.865Z · comments (2)
Cooperating with aliens and AGIs: An ECL explainer
Chi Nguyen · 2024-02-24T22:58:47.345Z · comments (8)
Unlearning via RMU is mostly shallow
Andy Arditi (andy-arditi) · 2024-07-23T16:07:52.223Z · comments (3)
Applications of Chaos: Saying No (with Hastings Greer)
Elizabeth (pktechgirl) · 2024-09-21T16:30:07.415Z · comments (16)
Consent across power differentials
Ramana Kumar (ramana-kumar) · 2024-07-09T11:42:03.177Z · comments (12)
Low Probability Estimation in Language Models
Gabriel Wu (gabriel-wu) · 2024-10-18T15:50:05.947Z · comments (0)
[link] A toy evaluation of inference code tampering
Fabien Roger (Fabien) · 2024-12-09T17:43:40.910Z · comments (0)
Changes in College Admissions
Zvi · 2024-04-24T13:50:03.487Z · comments (11)
AI #52: Oops
Zvi · 2024-02-22T21:50:07.393Z · comments (9)
[link] on the dollar-yen exchange rate
bhauth · 2024-04-07T04:49:53.920Z · comments (21)
A Solution for AGI/ASI Safety
Weibing Wang (weibing-wang) · 2024-12-18T19:44:29.739Z · comments (30)
On Complexity Science
Garrett Baker (D0TheMath) · 2024-04-05T02:24:32.039Z · comments (19)
[link] Finding Backward Chaining Circuits in Transformers Trained on Tree Search
abhayesian · 2024-05-28T05:29:46.777Z · comments (1)
[link] Can AI Outpredict Humans? Results From Metaculus's Q3 AI Forecasting Benchmark
ChristianWilliams · 2024-10-10T18:58:46.041Z · comments (2)
Phallocentricity in GPT-J's bizarre stratified ontology
mwatkins · 2024-02-17T00:16:15.649Z · comments (37)
Vipassana Meditation and Active Inference: A Framework for Understanding Suffering and its Cessation
Benjamin Sturgeon (benjamin-sturgeon) · 2024-03-21T12:32:22.475Z · comments (8)
Sherlockian Abduction Master List
Cole Wyeth (Amyr) · 2024-07-11T20:27:00.000Z · comments (63)
[link] [Paper Blogpost] When Your AIs Deceive You: Challenges with Partial Observability in RLHF
Leon Lang (leon-lang) · 2024-10-22T13:57:41.125Z · comments (2)
DeekSeek v3: The Six Million Dollar Model
Zvi · 2024-12-31T15:10:06.924Z · comments (6)
[Intuitive self-models] 7. Hearing Voices, and Other Hallucinations
Steven Byrnes (steve2152) · 2024-10-29T13:36:16.325Z · comments (2)
[link] Announcing Human-aligned AI Summer School
Jan_Kulveit · 2024-05-22T08:55:10.839Z · comments (0)
Observations on Teaching for Four Weeks
ClareChiaraVincent · 2024-05-06T16:55:59.315Z · comments (14)
Scenario Forecasting Workshop: Materials and Learnings
elifland · 2024-03-08T02:30:46.517Z · comments (3)
Transfer learning and generalization-qua-capability in Babbage and Davinci (or, why division is better than Spanish)
RP (Complex Bubble Tea) · 2024-02-09T07:00:45.825Z · comments (6)
AI #82: The Governor Ponders
Zvi · 2024-09-19T13:30:04.863Z · comments (8)
The Fragility of Life Hypothesis and the Evolution of Cooperation
KristianRonn · 2024-09-04T21:04:49.878Z · comments (6)
Paper in Science: Managing extreme AI risks amid rapid progress
JanB (JanBrauner) · 2024-05-23T08:40:40.678Z · comments (2)
Exercise: Planmaking, Surprise Anticipation, and "Baba is You"
Raemon · 2024-02-24T20:33:49.574Z · comments (20)
Why you should learn a musical instrument
cata · 2024-05-15T20:36:16.034Z · comments (23)
An issue with training schemers with supervised fine-tuning
Fabien Roger (Fabien) · 2024-06-27T15:37:56.020Z · comments (12)
[link] Evaluating Stability of Unreflective Alignment
james.lucassen · 2024-02-01T22:15:40.902Z · comments (11)
Wrong answer bias
lemonhope (lcmgcd) · 2024-02-01T20:05:38.573Z · comments (24)
[link] in defense of Linus Pauling
bhauth · 2024-06-03T21:27:43.962Z · comments (8)
Work with me on agent foundations: independent fellowship
Alex_Altair · 2024-09-21T13:59:16.706Z · comments (5)
[link] Book review: Xenosystems
jessicata (jessica.liu.taylor) · 2024-09-16T20:17:56.670Z · comments (18)
← previous page (newer posts) · next page (older posts) →