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] Validating / finding alignment-relevant concepts using neural data
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-09-20T21:12:49.267Z · comments (0)
Piling bounded arguments
momom2 (amaury-lorin) · 2024-09-19T22:27:41.534Z · comments (0)
[link] In-Context Learning: An Alignment Survey
alamerton · 2024-09-30T18:44:28.589Z · comments (0)
Of Birds and Bees
RussellThor · 2024-09-30T10:52:15.069Z · comments (9)
Prediction markets and Taxes
Edmund Nelson (edmund-nelson) · 2024-11-01T17:39:35.191Z · comments (7)
[link] Taking nonlogical concepts seriously
Kris Brown (kris-brown) · 2024-10-15T18:16:01.226Z · comments (5)
[link] [Linkpost] Hawkish nationalism vs international AI power and benefit sharing
jakub_krys (kryjak) · 2024-10-18T18:13:19.425Z · comments (5)
Foresight Vision Weekend 2024
Allison Duettmann (allison-duettmann) · 2024-10-01T21:59:55.107Z · 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)
Quantitative Trading Bootcamp [Nov 6-10]
Ricki Heicklen (bayesshammai) · 2024-10-28T18:39:58.480Z · comments (0)
[question] If I ask an LLM to think step by step, how big are the steps?
ryan_b · 2024-09-13T20:30:50.558Z · answers+comments (1)
[link] Species as Canonical Referents of Super-Organisms
Yudhister Kumar (randomwalks) · 2024-10-18T07:49:52.944Z · comments (8)
Enhancing Mathematical Modeling with LLMs: Goals, Challenges, and Evaluations
ozziegooen · 2024-10-28T21:44:42.352Z · comments (0)
[question] What actual bad outcome has "ethics-based" RLHF AI Alignment already prevented?
Roko · 2024-10-19T06:11:12.602Z · answers+comments (16)
[link] October 2024 Progress in Guaranteed Safe AI
Quinn (quinn-dougherty) · 2024-10-28T23:34:51.689Z · comments (0)
[link] Thinking LLMs: General Instruction Following with Thought Generation
Bogdan Ionut Cirstea (bogdan-ionut-cirstea) · 2024-10-15T09:21:22.583Z · comments (0)
[link] Consciousness As Recursive Reflections
Gunnar_Zarncke · 2024-10-05T20:00:53.053Z · comments (3)
A Brief Explanation of AI Control
Aaron_Scher · 2024-10-22T07:00:56.954Z · 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)
[question] What makes one a "rationalist"?
mathyouf · 2024-10-08T20:25:21.812Z · answers+comments (5)
[question] somebody explain the word "epistemic" to me
KvmanThinking (avery-liu) · 2024-10-28T16:40:24.275Z · answers+comments (8)
Moral Trade, Impact Distributions and Large Worlds
Larks · 2024-09-20T03:45:56.273Z · comments (0)
The Personal Implications of AGI Realism
xizneb · 2024-10-20T16:43:37.870Z · comments (7)
The Great Bootstrap
KristianRonn · 2024-10-11T19:46:51.752Z · comments (0)
Testing "True" Language Understanding in LLMs: A Simple Proposal
MtryaSam · 2024-11-02T19:12:34.710Z · comments (2)
[link] Boons and banes
dkl9 · 2024-09-23T06:18:38.335Z · comments (0)
[link] Optimising under arbitrarily many constraint equations
dkl9 · 2024-09-12T14:59:28.475Z · comments (0)
[link] Redundant Attention Heads in Large Language Models For In Context Learning
skunnavakkam · 2024-09-01T20:08:48.963Z · comments (0)
Against Job Boards: Human Capital and the Legibility Trap
vaishnav92 · 2024-10-24T20:50:50.266Z · comments (1)
The Existential Dread of Being a Powerful AI System
testingthewaters · 2024-09-26T10:56:32.904Z · comments (1)
Avoiding jailbreaks by discouraging their representation in activation space
Guido Bergman · 2024-09-27T17:49:20.785Z · comments (2)
Increasing the Span of the Set of Ideas
Jeffrey Heninger (jeffrey-heninger) · 2024-09-13T15:52:39.132Z · comments (1)
Introducing Kairos: a new AI safety fieldbuilding organization (the new home for SPAR and FSP)
agucova · 2024-10-25T21:59:08.782Z · comments (0)
GPT4o is still sensitive to user-induced bias when writing code
Reed (ThomasReed) · 2024-09-22T21:04:54.717Z · comments (0)
Goal: Understand Intelligence
Johannes C. Mayer (johannes-c-mayer) · 2024-11-03T21:20:02.900Z · comments (8)
A gentle introduction to sparse autoencoders
Nick Jiang (nick-jiang) · 2024-09-02T18:11:47.086Z · comments (0)
Inquisitive vs. adversarial rationality
gb (ghb) · 2024-09-18T13:50:09.198Z · comments (9)
[question] Is School of Thought related to the Rationality Community?
Shoshannah Tekofsky (DarkSym) · 2024-10-15T12:41:33.224Z · answers+comments (6)
Grounding self-reference paradoxes in reality
Fiora from Rosebloom · 2024-09-29T05:50:30.559Z · comments (3)
Exploring Shard-like Behavior: Empirical Insights into Contextual Decision-Making in RL Agents
Alejandro Aristizabal (alejandro-aristizabal) · 2024-09-29T00:32:42.161Z · comments (0)
Food, Prison & Exotic Animals: Sparse Autoencoders Detect 6.5x Performing Youtube Thumbnails
Louka Ewington-Pitsos (louka-ewington-pitsos) · 2024-09-17T03:52:43.269Z · comments (2)
[link] Contra Yudkowsky on 2-4-6 Game Difficulty Explanations
Josh Hickman (josh-hickman) · 2024-09-08T16:13:33.187Z · comments (1)
[link] [Linkpost] Interpretable Analysis of Features Found in Open-source Sparse Autoencoder (partial replication)
Fernando Avalos (fernando-avalos) · 2024-09-09T03:33:53.548Z · comments (1)
[question] why won't this alignment plan work?
KvmanThinking (avery-liu) · 2024-10-10T15:44:59.450Z · answers+comments (7)
Thoughts on Evo-Bio Math and Mesa-Optimization: Maybe We Need To Think Harder About "Relative" Fitness?
Lorec · 2024-09-28T14:07:42.412Z · comments (6)
'Chat with impactful research & evaluations' (Unjournal NotebookLMs)
david reinstein (david-reinstein) · 2024-09-28T00:32:16.845Z · comments (0)
[question] Can subjunctive dependence emerge from a simplicity prior?
Daniel C (harper-owen) · 2024-09-16T12:39:35.543Z · answers+comments (0)
[link] AI Safety Newsletter #43: White House Issues First National Security Memo on AI Plus, AI and Job Displacement, and AI Takes Over the Nobels
Corin Katzke (corin-katzke) · 2024-10-28T16:03:39.258Z · comments (0)
Thirty random thoughts about AI alignment
Lysandre Terrisse · 2024-09-15T16:24:10.572Z · comments (1)
[link] SCP Foundation - Anti memetic Division Hub
landscape_kiwi · 2024-09-15T13:40:52.691Z · comments (1)
← previous page (newer posts) · next page (older posts) →