~www_lesswrong_com | Bookmarks (687)
-
Reinforcement Learning: Essential Step Towards AGI or Irrelevant? — LessWrong
Published on October 17, 2024 3:37 AM GMTA friend of mine thinks that RL is a...
-
The Cognitive Bootcamp Agreement — LessWrong
Published on October 16, 2024 11:24 PM GMTFor the next Cognitive Bootcamp, I wanted to experiment...
-
Bitter lessons about lucid dreaming — LessWrong
Published on October 16, 2024 9:27 PM GMTThe amount of effort is not proportional to the...
-
Towards Quantitative AI Risk Management — LessWrong
Published on October 16, 2024 7:26 PM GMTReading guidelines: If you are short on time, just...
-
Improving Model-Written Evals for AI Safety Benchmarking — LessWrong
Published on October 15, 2024 6:25 PM GMTThis post was written as part of the summer...
-
Anthropic's updated Responsible Scaling Policy — LessWrong
Published on October 15, 2024 4:46 PM GMTToday we are publishing a significant update to our...
-
When is reward ever the optimization target? — LessWrong
Published on October 15, 2024 3:09 PM GMTAlright, I have a question stemming from TurnTrout's post...
-
An Opinionated Evals Reading List — LessWrong
Published on October 15, 2024 2:38 PM GMTWhile you can make a lot of progress in...
-
Anthropic's first RSP update — LessWrong
Published on October 15, 2024 2:25 PM GMTI am actively editing this post. Consider reading it...
-
[Intuitive self-models] 5. Dissociative Identity (Multiple Personality) Disorder — LessWrong
Published on October 15, 2024 1:31 PM GMT5.1 Post summary / Table of contentsThis is the...
-
Economics Roundup #4 — LessWrong
Published on October 15, 2024 1:20 PM GMTPrevious Economics Roundups: #1, #2, #3 Fun With Campaign...
-
Is School of Thought related to the Rationality Community? — LessWrong
Published on October 15, 2024 12:41 PM GMTIf so, who are they? Link: https://yourbias.is/ At a...
-
Inverse Problems In Everyday Life — LessWrong
Published on October 15, 2024 11:42 AM GMTThere’s a class of problems broadly known as inverse problems....
-
Thinking LLMs: General Instruction Following with Thought Generation — LessWrong
Published on October 15, 2024 9:21 AM GMTAuthors: Tianhao Wu, Janice Lan, Weizhe Yuan, Jiantao Jiao,...
-
The AGI Entente Delusion — LessWrong
Published on October 13, 2024 5:00 PM GMTAs humanity gets closer to Artificial General Intelligence (AGI),...
-
Parental Writing Selection Bias — LessWrong
Published on October 13, 2024 2:00 PM GMT In general I'd like to see a lot...
-
Personal Philosophy — LessWrong
Published on October 13, 2024 3:01 AM GMTThis is a rough outline of my philosophical framework....
-
AI Compute governance: Verifying AI chip location — LessWrong
Published on October 12, 2024 5:36 PM GMTTL;DR: In this post I discuss a recently proposed...
-
Contagious Beliefs—Simulating Political Alignment — LessWrong
Published on October 13, 2024 12:27 AM GMTHumans are social animals, and as such we are...
-
How Should We Use Limited Time to Maximize Long-Term Impact? — LessWrong
Published on October 12, 2024 8:02 PM GMTI've been reflecting on how researchers—particularly those with limited...
-
Binary encoding as a simple explicit construction for superposition — LessWrong
Published on October 12, 2024 9:18 PM GMTSuperposition is the possibility of storing more than n.mjx-chtml {display:...
-
A Percentage Model of a Person — LessWrong
Published on October 12, 2024 5:55 PM GMTThe standard psychological questionnaire for depression doctors have given...
-
Geoffrey Hinton on the Past, Present, and Future of AI — LessWrong
Published on October 12, 2024 4:41 PM GMTIntroductionGeoffrey Hinton is a famous AI researcher who is...
-
AI research assistants competition 2024Q3: Tie between Elicit and You.com — LessWrong
Published on October 12, 2024 3:10 PM GMT Summary I make a large part of my...