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) →

[link] Virtue is a Vector
robotelvis · 2024-09-10T03:02:45.737Z · comments (1)
Toy Models of Superposition: Simplified by Hand
Axel Sorensen (axel-sorensen) · 2024-09-29T21:19:52.475Z · comments (2)
[link] Molecular dynamics data will be essential for the next generation of ML protein models
Abhishaike Mahajan (abhishaike-mahajan) · 2024-08-26T14:50:23.790Z · comments (0)
how to rapidly assimilate new information
dhruvmethi · 2024-10-24T02:18:00.648Z · comments (3)
[link] Jailbreaking language models with user roleplay
loops (smitop) · 2024-09-28T23:43:10.870Z · comments (0)
On epistemic autonomy
sanyer (santeri-koivula) · 2024-08-31T18:50:43.377Z · comments (0)
[question] Change My Mind: Thirders in "Sleeping Beauty" are Just Doing Epistemology Wrong
DragonGod · 2024-10-16T10:20:22.133Z · answers+comments (67)
[link] Universal dimensions of visual representation
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-08-28T10:38:58.396Z · comments (0)
Two new datasets for evaluating political sycophancy in LLMs
alma.liezenga · 2024-09-28T18:29:49.088Z · comments (0)
The Geometric Importance of Side Payments
StrivingForLegibility · 2024-08-07T01:38:04.635Z · comments (4)
An open response to Wittkotter and Yampolskiy
Donald Hobson (donald-hobson) · 2024-09-24T22:27:21.987Z · comments (0)
[link] What is autonomy? Why boundaries are necessary.
Chipmonk · 2024-10-21T17:56:33.722Z · comments (1)
[link] AI Safety at the Frontier: Paper Highlights, July '24
gasteigerjo · 2024-08-05T13:00:46.028Z · comments (0)
[link] Can AI agents learn to be good?
Ram Rachum (ram@rachum.com) · 2024-08-29T14:20:04.336Z · comments (0)
On Intentionality, or: Towards a More Inclusive Concept of Lying
Cornelius Dybdahl (Kalciphoz) · 2024-10-18T10:37:32.201Z · comments (0)
Three main arguments that AI will save humans and one meta-argument
avturchin · 2024-10-02T11:39:08.910Z · comments (8)
[link] Nerdtrition: simple diets via spreadsheet abuse
dkl9 · 2024-10-27T21:45:15.117Z · comments (0)
[link] Triangulating My Interpretation of Methods: Black Boxes by Marco J. Nathan
adamShimi · 2024-10-09T19:13:26.631Z · comments (0)
Thinking About Propensity Evaluations
Maxime Riché (maxime-riche) · 2024-08-19T09:23:55.091Z · comments (0)
[link] Approval-Seeking ⇒ Playful Evaluation
Jonathan Moregård (JonathanMoregard) · 2024-08-28T21:03:51.244Z · comments (0)
LLMs are likely not conscious
research_prime_space · 2024-09-29T20:57:26.111Z · comments (7)
[link] AI Safety Newsletter #42: Newsom Vetoes SB 1047 Plus, OpenAI’s o1, and AI Governance Summary
Corin Katzke (corin-katzke) · 2024-10-01T20:35:32.399Z · comments (0)
MIT FutureTech are hiring for a Head of Operations role
peterslattery · 2024-10-02T17:11:42.960Z · comments (0)
[link] [Linkpost] Automated Design of Agentic Systems
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-08-19T23:06:06.669Z · comments (1)
[link] Models of life
Abhishaike Mahajan (abhishaike-mahajan) · 2024-09-29T19:24:40.060Z · comments (0)
[link] Michael Streamlines on Buddhism
Chris_Leong · 2024-08-09T04:44:52.126Z · comments (0)
Interpreting the effects of Jailbreak Prompts in LLMs
Harsh Raj (harsh-raj-ep-037) · 2024-09-29T19:01:10.113Z · comments (0)
Thoughts On the Nature of Capability Elicitation via Fine-tuning
Theodore Chapman · 2024-10-15T08:39:19.909Z · comments (0)
[link] It's important to know when to stop: Mechanistic Exploration of Gemma 2 List Generation
Gerard Boxo (gerard-boxo) · 2024-10-14T17:04:57.010Z · comments (0)
HDBSCAN is Surprisingly Effective at Finding Interpretable Clusters of the SAE Decoder Matrix
Jaehyuk Lim (jason-l) · 2024-10-11T23:06:14.340Z · comments (2)
Steering LLMs' Behavior with Concept Activation Vectors
Ruixuan Huang (sprout_ust) · 2024-09-28T09:53:19.658Z · comments (0)
Dario Amodei's "Machines of Loving Grace" sound incredibly dangerous, for Humans
Super AGI (super-agi) · 2024-10-27T05:05:13.763Z · comments (1)
[link] Checking public figures on whether they "answered the question" quick analysis from Harris/Trump debate, and a proposal
david reinstein (david-reinstein) · 2024-09-11T20:25:27.845Z · comments (4)
[link] Validating / finding alignment-relevant concepts using neural data
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-09-20T21:12:49.267Z · comments (0)
[link] Taking nonlogical concepts seriously
Kris Brown (kris-brown) · 2024-10-15T18:16:01.226Z · comments (5)
Enhancing Mathematical Modeling with LLMs: Goals, Challenges, and Evaluations
ozziegooen · 2024-10-28T21:44:42.352Z · comments (0)
[link] October 2024 Progress in Guaranteed Safe AI
Quinn (quinn-dougherty) · 2024-10-28T23:34:51.689Z · comments (0)
[link] In-Context Learning: An Alignment Survey
alamerton · 2024-09-30T18:44:28.589Z · comments (0)
Foresight Vision Weekend 2024
Allison Duettmann (allison-duettmann) · 2024-10-01T21:59:55.107Z · comments (0)
A Brief Explanation of AI Control
Aaron_Scher · 2024-10-22T07:00:56.954Z · comments (1)
Broadly human level, cognitively complete AGI
p.b. · 2024-08-06T09:26:13.220Z · comments (0)
[link] Boons and banes
dkl9 · 2024-09-23T06:18:38.335Z · comments (0)
Denver USA - ACX Meetups Everywhere Fall 2024
Eneasz · 2024-08-29T18:40:53.332Z · comments (0)
Fake Blog Posts as a Problem Solving Device
silentbob · 2024-08-31T09:22:54.513Z · comments (0)
[question] On the subject of in-house large language models versus implementing frontier models
Annapurna (jorge-velez) · 2024-09-23T15:00:32.811Z · answers+comments (1)
[link] Consciousness As Recursive Reflections
Gunnar_Zarncke · 2024-10-05T20:00:53.053Z · comments (3)
[link] Species as Canonical Referents of Super-Organisms
Yudhister Kumar (randomwalks) · 2024-10-18T07:49:52.944Z · comments (8)
Of Birds and Bees
RussellThor · 2024-09-30T10:52:15.069Z · comments (9)
[link] Cooperation and Alignment in Delegation Games: You Need Both!
Oliver Sourbut · 2024-08-03T10:16:51.716Z · comments (0)
Deception and Jailbreak Sequence: 2. Iterative Refinement Stages of Jailbreaks in LLM
Winnie Yang (winnie-yang) · 2024-08-28T08:41:38.967Z · comments (2)
← previous page (newer posts) · next page (older posts) →