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) →

Comments on Anthropic's Scaling Monosemanticity
Robert_AIZI · 2024-06-03T12:15:44.708Z · comments (8)
Explaining a Math Magic Trick
Robert_AIZI · 2024-05-05T19:41:52.048Z · comments (10)
OpenAI #8: The Right to Warn
Zvi · 2024-06-17T12:00:02.639Z · comments (8)
Access to powerful AI might make computer security radically easier
Buck · 2024-06-08T06:00:19.310Z · comments (14)
OpenAI's Sora is an agent
CBiddulph (caleb-biddulph) · 2024-02-16T07:35:52.171Z · comments (25)
Deceptive AI ≠ Deceptively-aligned AI
Steven Byrnes (steve2152) · 2024-01-07T16:55:13.761Z · comments (19)
The case for unlearning that removes information from LLM weights
Fabien Roger (Fabien) · 2024-10-14T14:08:04.775Z · comments (14)
[link] Compact Proofs of Model Performance via Mechanistic Interpretability
LawrenceC (LawChan) · 2024-06-24T19:27:21.214Z · comments (3)
On Claude 3.5 Sonnet
Zvi · 2024-06-24T12:00:05.719Z · comments (14)
[link] Ideological Bayesians
Kevin Dorst · 2024-02-25T14:17:25.070Z · comments (4)
[link] Ilya Sutskever created a new AGI startup
harfe · 2024-06-19T17:17:17.366Z · comments (35)
[link] Seven lessons I didn't learn from election day
Eric Neyman (UnexpectedValues) · 2024-11-14T18:39:07.053Z · comments (33)
[link] MIRI's April 2024 Newsletter
Harlan · 2024-04-12T23:38:20.781Z · comments (0)
[question] How to get nerds fascinated about mysterious chronic illness research?
riceissa · 2024-05-27T22:58:29.707Z · answers+comments (50)
I am the Golden Gate Bridge
Zvi · 2024-05-27T14:40:03.216Z · comments (6)
[link] Explaining Impact Markets
Saul Munn (saul-munn) · 2024-01-31T09:51:27.587Z · comments (2)
[link] I found >800 orthogonal "write code" steering vectors
Jacob G-W (g-w1) · 2024-07-15T19:06:17.636Z · comments (19)
[link] Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant
Olli Järviniemi (jarviniemi) · 2024-05-06T07:07:05.019Z · comments (13)
[link] Almost everyone I’ve met would be well-served thinking more about what to focus on
Henrik Karlsson (henrik-karlsson) · 2024-01-05T21:01:27.861Z · comments (8)
[link] RAND report finds no effect of current LLMs on viability of bioterrorism attacks
StellaAthena · 2024-01-25T19:17:30.493Z · comments (14)
[link] the Giga Press was a mistake
bhauth · 2024-08-21T04:51:24.150Z · comments (26)
Towards a Less Bullshit Model of Semantics
johnswentworth · 2024-06-17T15:51:06.060Z · comments (44)
It's time for a self-reproducing machine
Carl Feynman (carl-feynman) · 2024-08-07T21:52:22.819Z · comments (68)
Sparsify: A mechanistic interpretability research agenda
Lee Sharkey (Lee_Sharkey) · 2024-04-03T12:34:12.043Z · comments (22)
[link] Things You’re Allowed to Do: University Edition
Saul Munn (saul-munn) · 2024-02-06T00:36:11.690Z · comments (13)
Counting arguments provide no evidence for AI doom
Nora Belrose (nora-belrose) · 2024-02-27T23:03:49.296Z · comments (188)
[question] What are the best arguments for/against AIs being "slightly 'nice'"?
Raemon · 2024-09-24T02:00:19.605Z · answers+comments (56)
Apollo Research 1-year update
Marius Hobbhahn (marius-hobbhahn) · 2024-05-29T17:44:32.484Z · comments (0)
[link] Sabotage Evaluations for Frontier Models
David Duvenaud (david-duvenaud) · 2024-10-18T22:33:14.320Z · comments (55)
[link] Finishing The SB-1047 Documentary In 6 Weeks
Michaël Trazzi (mtrazzi) · 2024-10-28T20:17:47.465Z · comments (5)
A Solomonoff Inductor Walks Into a Bar: Schelling Points for Communication
johnswentworth · 2024-07-26T00:33:42.000Z · comments (1)
2024 Petrov Day Retrospective
Ben Pace (Benito) · 2024-09-28T21:30:14.952Z · comments (25)
[link] Anthropic: Three Sketches of ASL-4 Safety Case Components
Zach Stein-Perlman · 2024-11-06T16:00:06.940Z · comments (33)
You can, in fact, bamboozle an unaligned AI into sparing your life
David Matolcsi (matolcsid) · 2024-09-29T16:59:43.942Z · comments (171)
Notes on Dwarkesh Patel’s Podcast with Demis Hassabis
Zvi · 2024-03-01T16:30:08.687Z · comments (0)
[link] Against Aschenbrenner: How 'Situational Awareness' constructs a narrative that undermines safety and threatens humanity
GideonF · 2024-07-15T18:37:40.232Z · comments (17)
[link] Executable philosophy as a failed totalizing meta-worldview
jessicata (jessica.liu.taylor) · 2024-09-04T22:50:18.294Z · comments (40)
Takeoff speeds presentation at Anthropic
Tom Davidson (tom-davidson-1) · 2024-06-04T22:46:35.448Z · comments (0)
Science advances one funeral at a time
Cameron Berg (cameron-berg) · 2024-11-01T23:06:19.381Z · comments (9)
OpenAI: The Board Expands
Zvi · 2024-03-12T14:00:04.110Z · comments (1)
[question] Am I confused about the "malign universal prior" argument?
nostalgebraist · 2024-08-27T23:17:22.779Z · answers+comments (33)
Everything Wrong with Roko's Claims about an Engineered Pandemic
WitheringWeights (EZ97) · 2024-02-22T15:59:08.439Z · comments (10)
SB 1047: Final Takes and Also AB 3211
Zvi · 2024-08-27T22:10:07.647Z · comments (11)
On attunement
Joe Carlsmith (joekc) · 2024-03-25T12:47:34.856Z · comments (8)
New page: Integrity
Zach Stein-Perlman · 2024-07-10T15:00:41.050Z · comments (3)
Quotes from Leopold Aschenbrenner’s Situational Awareness Paper
Zvi · 2024-06-07T11:40:03.981Z · comments (10)
Zvi’s Thoughts on His 2nd Round of SFF
Zvi · 2024-11-20T13:40:08.092Z · comments (2)
Just admit that you’ve zoned out
joec · 2024-06-04T02:51:27.594Z · comments (22)
How to train your own "Sleeper Agents"
evhub · 2024-02-07T00:31:42.653Z · comments (11)
Meaning & Agency
abramdemski · 2023-12-19T22:27:32.123Z · comments (17)
← previous page (newer posts) · next page (older posts) →