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 Safety Chatbot
markov (markovial) · 2023-12-21T14:06:48.981Z · comments (11)
[link] Pay-on-results personal growth: first success
Chipmonk · 2024-09-14T03:39:12.975Z · comments (5)
Vote on worthwhile OpenAI topics to discuss
Ben Pace (Benito) · 2023-11-21T00:03:03.898Z · comments (55)
Natural Latents Are Not Robust To Tiny Mixtures
johnswentworth · 2024-06-07T18:53:36.643Z · comments (8)
Social status part 2/2: everything else
Steven Byrnes (steve2152) · 2024-03-05T16:29:19.072Z · comments (2)
Inspired by: Failures in Kindness
X4vier · 2024-07-27T01:21:42.848Z · comments (2)
Balsa Update and General Thank You
Zvi · 2023-12-12T20:30:03.980Z · comments (8)
[link] Dario Amodei — Machines of Loving Grace
Matrice Jacobine · 2024-10-11T21:43:31.448Z · comments (25)
Balancing Games
jefftk (jkaufman) · 2024-02-24T14:40:04.237Z · comments (18)
What is SB 1047 *for*?
Raemon · 2024-09-05T17:39:39.871Z · comments (8)
[question] We might be dropping the ball on Autonomous Replication and Adaptation.
Charbel-Raphaël (charbel-raphael-segerie) · 2024-05-31T13:49:11.327Z · answers+comments (30)
E.T. Jaynes Probability Theory: The logic of Science I
Jan Christian Refsgaard (jan-christian-refsgaard) · 2023-12-27T23:47:52.579Z · comments (20)
Managing risks while trying to do good
Wei Dai (Wei_Dai) · 2024-02-01T18:08:46.506Z · comments (26)
[link] Research Report: Sparse Autoencoders find only 9/180 board state features in OthelloGPT
Robert_AIZI · 2024-03-05T13:55:33.483Z · comments (24)
AI #78: Some Welcome Calm
Zvi · 2024-08-22T14:20:10.812Z · comments (15)
Base LLMs refuse too
Connor Kissane (ckkissane) · 2024-09-29T16:04:21.343Z · comments (20)
Interdictor Ship
lsusr · 2024-08-19T04:59:18.487Z · comments (9)
[link] How do open AI models affect incentive to race?
jessicata (jessica.liu.taylor) · 2024-05-07T00:33:20.658Z · comments (13)
"Epistemic range of motion" and LessWrong moderation
habryka (habryka4) · 2023-11-27T21:58:40.834Z · comments (3)
Automation collapse
Geoffrey Irving · 2024-10-21T14:50:54.500Z · comments (6)
Showing SAE Latents Are Not Atomic Using Meta-SAEs
Bart Bussmann (Stuckwork) · 2024-08-24T00:56:46.048Z · comments (9)
[link] Results from an Adversarial Collaboration on AI Risk (FRI)
Josh Rosenberg (josh-rosenberg) · 2024-03-11T20:00:24.642Z · comments (3)
There Should Be More Alignment-Driven Startups
Vaniver · 2024-05-31T02:05:06.799Z · comments (14)
Pollsters Should Publish Question Translations
jefftk (jkaufman) · 2024-09-08T22:10:04.932Z · comments (3)
What is "True Love"?
johnswentworth · 2024-08-18T16:05:47.358Z · comments (9)
[question] What do we know about the AI knowledge and views, especially about existential risk, of the new OpenAI board members?
Zvi · 2024-03-11T14:55:05.128Z · answers+comments (2)
On OpenAI Dev Day
Zvi · 2023-11-09T16:10:06.646Z · comments (0)
[link] Is Claude a mystic?
jessicata (jessica.liu.taylor) · 2024-06-07T04:27:09.118Z · comments (23)
Self-explaining SAE features
Dmitrii Kharlapenko (dmitrii-kharlapenko) · 2024-08-05T22:20:36.041Z · comments (13)
[Intuitive self-models] 4. Trance
Steven Byrnes (steve2152) · 2024-10-08T13:30:41.446Z · comments (6)
AI Alignment via Slow Substrates: Early Empirical Results With StarCraft II
Lester Leong (lester-leong) · 2024-10-14T04:05:05.096Z · comments (9)
[link] Linkpost: Memorandum on Advancing the United States’ Leadership in Artificial Intelligence
Nisan · 2024-10-25T04:37:00.828Z · comments (2)
0th Person and 1st Person Logic
Adele Lopez (adele-lopez-1) · 2024-03-10T00:56:14.446Z · comments (28)
An Actually Intuitive Explanation of the Oberth Effect
Isaac King (KingSupernova) · 2024-01-10T20:23:17.216Z · comments (33)
Originality vs. Correctness
alkjash · 2023-12-06T18:51:49.531Z · comments (17)
[link] on bacteria, on teeth
bhauth · 2024-09-30T15:56:56.830Z · comments (9)
5 Physics Problems
DaemonicSigil · 2024-03-18T08:05:45.971Z · comments (0)
Raemon's Deliberate (“Purposeful?”) Practice Club
Raemon · 2023-11-14T18:24:19.335Z · comments (11)
MATS Alumni Impact Analysis
utilistrutil · 2024-09-30T02:35:57.273Z · comments (6)
[link] AI, centralization, and the One Ring
owencb · 2024-09-13T14:00:16.126Z · comments (11)
[link] Towards shutdownable agents via stochastic choice
EJT (ElliottThornley) · 2024-07-08T10:14:24.452Z · comments (7)
Thoughts on SB-1047
ryan_greenblatt · 2024-05-29T23:26:14.392Z · comments (1)
[link] shoes with springs
bhauth · 2023-12-30T21:46:55.319Z · comments (6)
AI #81: Alpha Proteo
Zvi · 2024-09-12T13:00:07.958Z · comments (3)
D&D.Sci: The Mad Tyrant's Pet Turtles
abstractapplic · 2024-03-29T16:22:13.732Z · comments (18)
Rationalists are missing a core piece for agent-like structure (energy vs information overload)
tailcalled · 2024-08-17T09:57:19.370Z · comments (9)
[link] Linkpost: Surely you can be serious
kave · 2024-07-18T22:18:09.271Z · comments (8)
Approaching Human-Level Forecasting with Language Models
Fred Zhang (fred-zhang) · 2024-02-29T22:36:34.012Z · comments (6)
[link] Are There Examples of Overhang for Other Technologies?
Jeffrey Heninger (jeffrey-heninger) · 2023-12-13T21:48:08.954Z · comments (50)
New paper shows truthfulness & instruction-following don't generalize by default
joshc (joshua-clymer) · 2023-11-19T19:27:30.735Z · comments (0)
← previous page (newer posts) · next page (older posts) →