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) →

The Worst Form Of Government (Except For Everything Else We've Tried)
johnswentworth · 2024-03-17T18:11:38.374Z · comments (46)
When is a mind me?
Rob Bensinger (RobbBB) · 2024-04-17T05:56:38.482Z · comments (125)
The Dark Arts
lsusr · 2023-12-19T04:41:13.356Z · comments (49)
Loving a world you don’t trust
Joe Carlsmith (joekc) · 2024-06-18T19:31:36.581Z · comments (13)
An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2
Neel Nanda (neel-nanda-1) · 2024-07-07T17:39:35.064Z · comments (15)
"It's a 10% chance which I did 10 times, so it should be 100%"
egor.timatkov · 2024-11-18T01:14:27.738Z · comments (57)
Limitations on Formal Verification for AI Safety
Andrew Dickson · 2024-08-19T23:03:52.706Z · comments (60)
How it All Went Down: The Puzzle Hunt that took us way, way Less Online
A* (agendra) · 2024-06-02T08:01:40.109Z · comments (5)
[link] Simple probes can catch sleeper agents
Monte M (montemac) · 2024-04-23T21:10:47.784Z · comments (21)
[link] "AI achieves silver-medal standard solving International Mathematical Olympiad problems"
gjm · 2024-07-25T15:58:57.638Z · comments (38)
Processor clock speeds are not how fast AIs think
Ege Erdil (ege-erdil) · 2024-01-29T14:39:38.050Z · comments (55)
Why I don't believe in the placebo effect
transhumanist_atom_understander · 2024-06-10T02:37:07.776Z · comments (22)
On saying "Thank you" instead of "I'm Sorry"
Michael Cohn (michael-cohn) · 2024-07-08T03:13:50.663Z · comments (16)
The case for training frontier AIs on Sumerian-only corpus
Alexandre Variengien (alexandre-variengien) · 2024-01-15T16:40:22.011Z · comments (15)
A Dozen Ways to Get More Dakka
Davidmanheim · 2024-04-08T04:45:19.427Z · comments (11)
Notice When People Are Directionally Correct
Chris_Leong · 2024-01-14T14:12:37.090Z · comments (8)
My simple AGI investment & insurance strategy
lc · 2024-03-31T02:51:53.479Z · comments (27)
[link] "Can AI Scaling Continue Through 2030?", Epoch AI (yes)
gwern · 2024-08-24T01:40:32.929Z · comments (4)
Updatelessness doesn't solve most problems
Martín Soto (martinsq) · 2024-02-08T17:30:11.266Z · comments (43)
Near-mode thinking on AI
Olli Järviniemi (jarviniemi) · 2024-08-04T20:47:28.085Z · comments (8)
How I started believing religion might actually matter for rationality and moral philosophy
zhukeepa · 2024-08-23T17:40:47.341Z · comments (41)
Circuits in Superposition: Compressing many small neural networks into one
Lucius Bushnaq (Lblack) · 2024-10-14T13:06:14.596Z · comments (8)
An even deeper atheism
Joe Carlsmith (joekc) · 2024-01-11T17:28:31.843Z · comments (47)
A Shutdown Problem Proposal
johnswentworth · 2024-01-21T18:12:48.664Z · comments (61)
Community Notes by X
NicholasKees (nick_kees) · 2024-03-18T17:13:33.195Z · comments (15)
Things I've Grieved
Raemon · 2024-02-18T19:32:47.169Z · comments (6)
Pantheon Interface
NicholasKees (nick_kees) · 2024-07-08T19:03:51.681Z · comments (22)
[link] Bayesian Injustice
Kevin Dorst · 2023-12-14T15:44:08.664Z · comments (10)
[question] What do coherence arguments actually prove about agentic behavior?
sunwillrise (andrei-alexandru-parfeni) · 2024-06-01T09:37:28.451Z · answers+comments (35)
BIG-Bench Canary Contamination in GPT-4
Jozdien · 2024-10-22T15:40:48.166Z · comments (13)
Deep Forgetting & Unlearning for Safely-Scoped LLMs
scasper · 2023-12-05T16:48:18.177Z · comments (30)
[link] Steering Llama-2 with contrastive activation additions
Nina Panickssery (NinaR) · 2024-01-02T00:47:04.621Z · comments (29)
Apocalypse insurance, and the hardline libertarian take on AI risk
So8res · 2023-11-28T02:09:52.400Z · comments (38)
Do you believe in hundred dollar bills lying on the ground? Consider humming
Elizabeth (pktechgirl) · 2024-05-16T00:00:05.257Z · comments (22)
Parasites (not a metaphor)
lemonhope (lcmgcd) · 2024-08-08T20:07:13.593Z · comments (17)
Why I take short timelines seriously
NicholasKees (nick_kees) · 2024-01-28T22:27:21.098Z · comments (29)
[link] Investigating the Chart of the Century: Why is food so expensive?
Maxwell Tabarrok (maxwell-tabarrok) · 2024-08-16T13:21:23.596Z · comments (26)
Natural Latents: The Math
johnswentworth · 2023-12-27T19:03:01.923Z · comments (37)
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
Erik Jenner (ejenner) · 2024-06-04T15:50:47.475Z · comments (14)
RTFB: On the New Proposed CAIP AI Bill
Zvi · 2024-04-10T18:30:08.410Z · comments (14)
Awakening
lsusr · 2024-05-30T07:03:00.821Z · comments (79)
Efficient Dictionary Learning with Switch Sparse Autoencoders
Anish Mudide (anish-mudide) · 2024-07-22T18:45:53.502Z · comments (19)
AI catastrophes and rogue deployments
Buck · 2024-06-03T17:04:51.206Z · comments (16)
The Standard Analogy
Zack_M_Davis · 2024-06-03T17:15:42.327Z · comments (28)
[link] Miles Brundage resigned from OpenAI, and his AGI readiness team was disbanded
garrison · 2024-10-23T23:40:57.180Z · comments (1)
A List of 45+ Mech Interp Project Ideas from Apollo Research’s Interpretability Team
Lee Sharkey (Lee_Sharkey) · 2024-07-18T14:15:50.248Z · comments (18)
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)
[link] My Number 1 Epistemology Book Recommendation: Inventing Temperature
adamShimi · 2024-09-08T14:30:40.456Z · comments (18)
A bird's eye view of ARC's research
Jacob_Hilton · 2024-10-23T15:50:06.123Z · comments (12)
← previous page (newer posts) · next page (older posts) →