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) →

Review: Conor Moreton's "Civilization & Cooperation"
Duncan Sabien (Deactivated) (Duncan_Sabien) · 2024-05-26T19:32:43.131Z · comments (8)
[link] Sabotage Evaluations for Frontier Models
David Duvenaud (david-duvenaud) · 2024-10-18T22:33:14.320Z · comments (11)
Prediction Markets aren't Magic
SimonM · 2023-12-21T12:54:07.754Z · comments (29)
[link] Large Language Models can Strategically Deceive their Users when Put Under Pressure.
ReaderM · 2023-11-15T16:36:04.446Z · comments (8)
[link] Finishing The SB-1047 Documentary In 6 Weeks
Michaël Trazzi (mtrazzi) · 2024-10-28T20:17:47.465Z · comments (4)
Based Beff Jezos and the Accelerationists
Zvi · 2023-12-06T16:00:08.380Z · comments (29)
Partial value takeover without world takeover
KatjaGrace · 2024-04-05T06:20:03.961Z · comments (23)
Towards Multimodal Interpretability: Learning Sparse Interpretable Features in Vision Transformers
hugofry · 2024-04-29T20:57:35.127Z · comments (8)
Public Call for Interest in Mathematical Alignment
Davidmanheim · 2023-11-22T13:22:09.558Z · comments (9)
[link] New report: Safety Cases for AI
joshc (joshua-clymer) · 2024-03-20T16:45:27.984Z · comments (13)
Dragon Agnosticism
jefftk (jkaufman) · 2024-08-01T17:00:06.434Z · comments (60)
AI #73: Openly Evil AI
Zvi · 2024-07-18T14:40:05.770Z · comments (20)
story-based decision-making
bhauth · 2024-02-07T02:35:27.286Z · comments (11)
[link] Debating with More Persuasive LLMs Leads to More Truthful Answers
Akbir Khan (akbir-khan) · 2024-02-07T21:28:10.694Z · comments (14)
On the abolition of man
Joe Carlsmith (joekc) · 2024-01-18T18:17:06.201Z · comments (18)
[link] Executable philosophy as a failed totalizing meta-worldview
jessicata (jessica.liu.taylor) · 2024-09-04T22:50:18.294Z · comments (40)
Covert Malicious Finetuning
Tony Wang (tw) · 2024-07-02T02:41:51.698Z · comments (4)
Stagewise Development in Neural Networks
Jesse Hoogland (jhoogland) · 2024-03-20T19:54:06.181Z · comments (1)
Live Theory Part 0: Taking Intelligence Seriously
Sahil · 2024-06-26T21:37:10.479Z · comments (3)
Singular learning theory: exercises
Zach Furman (zfurman) · 2024-08-30T20:00:03.785Z · comments (5)
Teaching CS During Take-Off
andrew carle (andrew-carle) · 2024-05-14T22:45:39.447Z · comments (13)
[link] I found >800 orthogonal "write code" steering vectors
Jacob G-W (g-w1) · 2024-07-15T19:06:17.636Z · comments (19)
We might be missing some key feature of AI takeoff; it'll probably seem like "we could've seen this coming"
Lukas_Gloor · 2024-05-09T15:43:11.490Z · comments (36)
Growth and Form in a Toy Model of Superposition
Liam Carroll (liam-carroll) · 2023-11-08T11:08:04.359Z · comments (7)
Solving adversarial attacks in computer vision as a baby version of general AI alignment
Stanislav Fort (stanislavfort) · 2024-08-29T17:17:47.136Z · comments (8)
Natural Latents: The Concepts
johnswentworth · 2024-03-20T18:21:19.878Z · comments (18)
[link] Re: Anthropic's suggested SB-1047 amendments
RobertM (T3t) · 2024-07-27T22:32:39.447Z · comments (13)
[link] More Hyphenation
Arjun Panickssery (arjun-panickssery) · 2024-02-07T19:43:29.086Z · comments (19)
How well do truth probes generalise?
mishajw · 2024-02-24T14:12:19.729Z · comments (11)
[link] Detecting Genetically Engineered Viruses With Metagenomic Sequencing
jefftk (jkaufman) · 2024-06-27T14:01:34.868Z · comments (10)
Research update: Towards a Law of Iterated Expectations for Heuristic Estimators
Eric Neyman (UnexpectedValues) · 2024-10-07T19:29:29.033Z · comments (2)
[link] Self-Help Corner: Loop Detection
adamShimi · 2024-10-02T08:33:23.487Z · comments (6)
2024 Petrov Day Retrospective
Ben Pace (Benito) · 2024-09-28T21:30:14.952Z · comments (25)
I'm a bit skeptical of AlphaFold 3
Oleg Trott (oleg-trott) · 2024-06-25T00:04:41.274Z · comments (14)
OpenAI: Helen Toner Speaks
Zvi · 2024-05-30T21:10:02.938Z · comments (8)
GPT-o1
Zvi · 2024-09-16T13:40:06.236Z · comments (34)
The Aspiring Rationalist Congregation
maia · 2024-01-10T22:52:54.298Z · comments (23)
There is a globe in your LLM
jacob_drori (jacobcd52) · 2024-10-08T00:43:40.300Z · comments (4)
Apply to be a Safety Engineer at Lockheed Martin!
yanni kyriacos (yanni) · 2024-03-31T21:02:08.499Z · comments (3)
Addressing Feature Suppression in SAEs
Benjamin Wright (Benw8888) · 2024-02-16T18:32:51.927Z · comments (3)
[link] Dario Amodei’s prepared remarks from the UK AI Safety Summit, on Anthropic’s Responsible Scaling Policy
Zac Hatfield-Dodds (zac-hatfield-dodds) · 2023-11-01T18:10:31.110Z · comments (1)
[Valence series] 2. Valence & Normativity
Steven Byrnes (steve2152) · 2023-12-07T16:43:49.919Z · comments (5)
[question] What are the best arguments for/against AIs being "slightly 'nice'"?
Raemon · 2024-09-24T02:00:19.605Z · answers+comments (51)
Scalable oversight as a quantitative rather than qualitative problem
Buck · 2024-07-06T17:42:41.325Z · comments (11)
A simple case for extreme inner misalignment
Richard_Ngo (ricraz) · 2024-07-13T15:40:37.518Z · comments (41)
Rejecting Television
Declan Molony (declan-molony) · 2024-04-23T04:59:50.253Z · comments (10)
[link] Environmentalism in the United States Is Unusually Partisan
Jeffrey Heninger (jeffrey-heninger) · 2024-05-13T21:23:10.755Z · comments (26)
[link] Anxiety vs. Depression
Sable · 2024-03-17T00:15:08.255Z · comments (35)
Reflections on Less Online
Error · 2024-07-07T03:49:44.534Z · comments (15)
[link] Nietzsche's Morality in Plain English
Arjun Panickssery (arjun-panickssery) · 2023-12-04T00:57:42.839Z · comments (13)
← previous page (newer posts) · next page (older posts) →