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) →

AI Alignment Metastrategy
Vanessa Kosoy (vanessa-kosoy) · 2023-12-31T12:06:11.433Z · comments (13)
[question] Which skincare products are evidence-based?
Vanessa Kosoy (vanessa-kosoy) · 2024-05-02T15:22:12.597Z · answers+comments (47)
Talent Needs of Technical AI Safety Teams
yams (william-brewer) · 2024-05-24T00:36:40.486Z · comments (64)
Anthropic's Certificate of Incorporation
Zach Stein-Perlman · 2024-06-12T13:00:30.806Z · comments (4)
BIG-Bench Canary Contamination in GPT-4
Jozdien · 2024-10-22T15:40:48.166Z · comments (12)
8 examples informing my pessimism on uploading without reverse engineering
Steven Byrnes (steve2152) · 2023-11-03T20:03:50.450Z · comments (12)
The LessWrong 2022 Review
habryka (habryka4) · 2023-12-05T04:00:00.000Z · comments (43)
[link] Anthropic release Claude 3, claims >GPT-4 Performance
LawrenceC (LawChan) · 2024-03-04T18:23:54.065Z · comments (41)
Why I funded PIBBSS
Ryan Kidd (ryankidd44) · 2024-09-15T19:56:33.018Z · comments (20)
[link] My Number 1 Epistemology Book Recommendation: Inventing Temperature
adamShimi · 2024-09-08T14:30:40.456Z · comments (18)
Current AIs Provide Nearly No Data Relevant to AGI Alignment
Thane Ruthenis · 2023-12-15T20:16:09.723Z · comments (155)
Mapping the semantic void: Strange goings-on in GPT embedding spaces
mwatkins · 2023-12-14T13:10:22.691Z · comments (31)
Rationality Research Report: Towards 10x OODA Looping?
Raemon · 2024-02-24T21:06:38.703Z · comments (21)
[link] Gender Exploration
sapphire (deluks917) · 2024-01-14T18:57:32.893Z · comments (25)
[link] introduction to cancer vaccines
bhauth · 2024-05-05T01:06:16.972Z · comments (19)
The Pareto Best and the Curse of Doom
Screwtape · 2024-02-21T23:10:01.359Z · comments (21)
How much to update on recent AI governance moves?
habryka (habryka4) · 2023-11-16T23:46:01.601Z · comments (5)
Four visions of Transformative AI success
Steven Byrnes (steve2152) · 2024-01-17T20:45:46.976Z · comments (22)
Simple versus Short: Higher-order degeneracy and error-correction
Daniel Murfet (dmurfet) · 2024-03-11T07:52:46.307Z · comments (6)
The Parable Of The Fallen Pendulum - Part 1
johnswentworth · 2024-03-01T00:25:00.111Z · comments (32)
[link] Practically A Book Review: Appendix to "Nonlinear's Evidence: Debunking False and Misleading Claims" (ThingOfThings)
tailcalled · 2024-01-03T17:07:13.990Z · comments (25)
Social status part 1/2: negotiations over object-level preferences
Steven Byrnes (steve2152) · 2024-03-05T16:29:07.143Z · comments (15)
The Pearly Gates
lsusr · 2024-05-30T04:01:14.198Z · comments (6)
Introduction to French AI Policy
Lucie Philippon (lucie-philippon) · 2024-07-04T03:39:45.273Z · comments (12)
The case for more ambitious language model evals
Jozdien · 2024-01-30T00:01:13.876Z · comments (30)
Ten arguments that AI is an existential risk
KatjaGrace · 2024-08-13T17:00:03.397Z · comments (41)
[link] A primer on the current state of longevity research
Abhishaike Mahajan (abhishaike-mahajan) · 2024-08-22T17:14:57.990Z · comments (6)
Being nicer than Clippy
Joe Carlsmith (joekc) · 2024-01-16T19:44:23.893Z · comments (32)
Experiences and learnings from both sides of the AI safety job market
Marius Hobbhahn (marius-hobbhahn) · 2023-11-15T15:40:32.196Z · comments (4)
What I Would Do If I Were Working On AI Governance
johnswentworth · 2023-12-08T06:43:42.565Z · comments (32)
You should go to ML conferences
Jan_Kulveit · 2024-07-24T11:47:52.214Z · comments (13)
Please stop using mediocre AI art in your posts
Raemon · 2024-08-25T00:13:52.890Z · comments (24)
' petertodd'’s last stand: The final days of open GPT-3 research
mwatkins · 2024-01-22T18:47:00.710Z · comments (16)
A Selection of Randomly Selected SAE Features
CallumMcDougall (TheMcDouglas) · 2024-04-01T09:09:49.235Z · comments (2)
"AI Alignment" is a Dangerously Overloaded Term
Roko · 2023-12-15T14:34:29.850Z · comments (100)
Clarifying METR's Auditing Role
Beth Barnes (beth-barnes) · 2024-05-30T18:41:56.029Z · comments (1)
Fact Finding: Attempting to Reverse-Engineer Factual Recall on the Neuron Level (Post 1)
Neel Nanda (neel-nanda-1) · 2023-12-23T02:44:24.270Z · comments (8)
[link] Please support this blog (with money)
Elizabeth (pktechgirl) · 2024-08-17T15:30:05.641Z · comments (2)
Attitudes about Applied Rationality
Camille Berger (Camille Berger) · 2024-02-03T14:42:22.770Z · comments (18)
The Leopold Model: Analysis and Reactions
Zvi · 2024-06-14T15:10:03.480Z · comments (19)
OthelloGPT learned a bag of heuristics
jylin04 · 2024-07-02T09:12:56.377Z · comments (10)
[link] Perplexity wins my AI race
Elizabeth (pktechgirl) · 2024-08-24T19:20:10.859Z · comments (12)
[question] How do you feel about LessWrong these days? [Open feedback thread]
jacobjacob · 2023-12-05T20:54:42.317Z · answers+comments (281)
Stuxnet, not Skynet: Humanity's disempowerment by AI
Roko · 2023-11-04T22:23:55.428Z · comments (24)
Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight
Sam Marks (samuel-marks) · 2024-04-18T16:17:39.136Z · comments (10)
A bird's eye view of ARC's research
Jacob_Hilton · 2024-10-23T15:50:06.123Z · comments (12)
[link] Most smart and skilled people are outside of the EA/rationalist community: an analysis
titotal (lombertini) · 2024-07-12T12:13:56.215Z · comments (36)
2023 in AI predictions
jessicata (jessica.liu.taylor) · 2024-01-01T05:23:42.514Z · comments (35)
New LessWrong feature: Dialogue Matching
jacobjacob · 2023-11-16T21:27:16.763Z · comments (22)
Why I'm doing PauseAI
Joseph Miller (Josephm) · 2024-04-30T16:21:54.156Z · comments (16)
← previous page (newer posts) · next page (older posts) →