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 the Debate Between Jezos and Leahy
Zvi · 2024-02-06T14:40:05.487Z · comments (6)
Announcing New Beginner-friendly Book on AI Safety and Risk
Darren McKee · 2023-11-25T15:57:08.078Z · comments (2)
[link] DeepMind: Frontier Safety Framework
Zach Stein-Perlman · 2024-05-17T17:30:02.504Z · comments (0)
On the Gladstone Report
Zvi · 2024-03-20T19:50:05.186Z · comments (11)
A gentle introduction to mechanistic anomaly detection
Erik Jenner (ejenner) · 2024-04-03T23:06:16.778Z · comments (2)
SAEs (usually) Transfer Between Base and Chat Models
Connor Kissane (ckkissane) · 2024-07-18T10:29:46.138Z · comments (0)
[Interim research report] Activation plateaus & sensitive directions in GPT2
StefanHex (Stefan42) · 2024-07-05T17:05:25.631Z · comments (2)
[link] A free to enter, 240 character, open-source iterated prisoner's dilemma tournament
Isaac King (KingSupernova) · 2023-11-09T08:24:43.277Z · comments (19)
A to Z of things
KatjaGrace · 2023-11-17T05:20:03.134Z · comments (6)
Generalization, from thermodynamics to statistical physics
Jesse Hoogland (jhoogland) · 2023-11-30T21:28:50.089Z · comments (9)
[link] Investigating an insurance-for-AI startup
L Rudolf L (LRudL) · 2024-09-21T15:29:10.083Z · comments (0)
Another argument against utility-centric alignment paradigms
Fiora from Rosebloom · 2024-09-22T07:28:27.856Z · comments (39)
[link] A primer on why computational predictive toxicology is hard
Abhishaike Mahajan (abhishaike-mahajan) · 2024-08-19T17:16:37.735Z · comments (2)
[link] Moving on from community living
Vika · 2024-04-17T17:02:11.357Z · comments (7)
On Llama-3 and Dwarkesh Patel’s Podcast with Zuckerberg
Zvi · 2024-04-22T13:10:02.645Z · comments (4)
[question] Is cybercrime really costing trillions per year?
Fabien Roger (Fabien) · 2024-09-27T08:44:07.621Z · answers+comments (28)
Bayesian updating in real life is mostly about understanding your hypotheses
Max H (Maxc) · 2024-01-01T00:10:30.978Z · comments (4)
[link] On Shifgrethor
JustisMills · 2024-10-27T15:30:13.688Z · comments (10)
[link] Improving Dictionary Learning with Gated Sparse Autoencoders
Senthooran Rajamanoharan (SenR) · 2024-04-25T18:43:47.003Z · comments (38)
Against most, but not all, AI risk analogies
Matthew Barnett (matthew-barnett) · 2024-01-14T03:36:16.267Z · comments (41)
What mistakes has the AI safety movement made?
EuanMcLean (euanmclean) · 2024-05-23T11:19:02.717Z · comments (29)
AI research assistants competition 2024Q3: Tie between Elicit and You.com
Elizabeth (pktechgirl) · 2024-10-12T15:10:05.417Z · comments (2)
AiPhone
Zvi · 2024-06-12T22:20:02.141Z · comments (4)
Self-Awareness: Taxonomy and eval suite proposal
Daniel Kokotajlo (daniel-kokotajlo) · 2024-02-17T01:47:01.802Z · comments (2)
[link] Ice: The Penultimate Frontier
Roko · 2024-07-13T23:44:56.827Z · comments (56)
A framework for thinking about AI power-seeking
Joe Carlsmith (joekc) · 2024-07-24T22:41:01.685Z · comments (15)
Black Box Biology
GeneSmith · 2023-11-29T02:27:29.794Z · comments (30)
On coincidences and Bayesian reasoning, as applied to the origins of COVID-19
viking_math · 2024-02-19T01:14:06.772Z · comments (28)
Thoughts on open source AI
Sam Marks (samuel-marks) · 2023-11-03T15:35:42.067Z · comments (17)
Automation collapse
Geoffrey Irving · 2024-10-21T14:50:54.500Z · comments (6)
What is a Tool?
johnswentworth · 2024-06-25T23:40:07.483Z · comments (4)
Don't sleep on Coordination Takeoffs
trevor (TrevorWiesinger) · 2024-01-27T19:55:26.831Z · comments (24)
Catastrophic Goodhart in RL with KL penalty
Thomas Kwa (thomas-kwa) · 2024-05-15T00:58:20.763Z · comments (10)
[link] Twitter thread on AI safety evals
Richard_Ngo (ricraz) · 2024-07-31T00:18:14.076Z · comments (3)
AI #55: Keep Clauding Along
Zvi · 2024-03-14T15:40:09.335Z · comments (16)
Never Drop A Ball
Screwtape · 2023-11-23T04:15:35.834Z · comments (1)
Book Review: On the Edge: The Future
Zvi · 2024-09-27T14:00:05.279Z · comments (1)
Three Notions of "Power"
johnswentworth · 2024-10-30T06:10:08.326Z · comments (22)
All About Concave and Convex Agents
mako yass (MakoYass) · 2024-03-24T21:37:17.922Z · comments (23)
[link] Outrage Bonding
Jonathan Moregård (JonathanMoregard) · 2024-08-09T13:46:59.818Z · comments (12)
[link] Pay-on-results personal growth: first success
Chipmonk · 2024-09-14T03:39:12.975Z · comments (5)
Do not delete your misaligned AGI.
mako yass (MakoYass) · 2024-03-24T21:37:07.724Z · comments (13)
RTFB: California’s AB 3211
Zvi · 2024-07-30T13:10:03.853Z · comments (2)
[link] Superforecasting the Origins of the Covid-19 Pandemic
DanielFilan · 2024-03-12T19:01:15.914Z · comments (0)
What is SB 1047 *for*?
Raemon · 2024-09-05T17:39:39.871Z · comments (8)
Managing risks while trying to do good
Wei Dai (Wei_Dai) · 2024-02-01T18:08:46.506Z · comments (26)
[link] on bacteria, on teeth
bhauth · 2024-09-30T15:56:56.830Z · comments (9)
[link] Dario Amodei — Machines of Loving Grace
Matrice Jacobine · 2024-10-11T21:43:31.448Z · comments (26)
AI Safety Chatbot
markov (markovial) · 2023-12-21T14:06:48.981Z · comments (11)
Offering AI safety support calls for ML professionals
Vael Gates · 2024-02-15T23:48:12.797Z · comments (1)
← previous page (newer posts) · next page (older posts) →