curius graph

all pages

showing 34251-34300 of 160880 pages (sorted by popularity)
Mechanistic Transparency for Machine Learning
goodfire.ai/blog/sae-open-source-announcement
Chargemaster - Wikipedia
Pīti - Wikipedia
Zohran Mamdani's policies are Very Bad - Rich in Thought
Get Numb Before You Get Good - Commoncog
Who We Are - 天火
How I wrote my first research paper | by neuralnetworks | Jul, 2025 | Medium
Predicting Predictions with Datamodels – gradient science
Fuck willpower - by Cate Hall - Useful Fictions
The Grok chatbot spewed racist and antisemitic content : NPR
I Wish I Didn't Miss the '90s-00s Internet | rohan ganapavarapu
Singapore Tourism Board and OpenAI sign MOU to prepare tourism sector for AI-driven future - Travel Trade Journal
Galois - Specifications Don't Exist
Reward Is Not the Optimization Target
No Universally Compelling Arguments
Introducing Stargate Norway | OpenAI
If you can generate obfuscated chain-of-thought, can you monitor it? — LessWrong
Fact Finding: Simplifying the Circuit (Post 2) — LessWrong
on becoming a computer
The state of LLM ethical decision-making - imbue
OpenAI’s GPT-5 Launch Causes Backlash Due to Colder Responses - The New York Times
Opinion | How ChatGPT Surprised Me - The New York Times
A Teen Was Suicidal. ChatGPT Was the Friend He Confided In. - The New York Times
Norman Mu | Adversarial Patches for Deep Neural Networks
Tracing Attention Computation Through Feature Interactions
Getting Started with Distributed Checkpoint (DCP) — PyTorch Tutorials 2.8.0+cu128 documentation
From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
So you want to be a wizard
Nepali troops deployed amid mass Gen Z protests : NPR
Opinion | FDA Director Marty Makary: I’m Cracking Down on Pharma Ads - The New York Times
Eric Zelikman on X: "human-centered AGI" / Twitter
Automatically Jailbreaking Frontier Language Models with Investigator Agents | Transluce AI
Modern Freedom Beats Feudal Serfdom - Human Progress
"The Use of Knowledge in Society" - Econlib
Goodhart Taxonomy - LessWrong 2.0 viewer
If anyone builds it, everyone will plausibly be fine - LessWrong 2.0 viewer
The Influenza Of Evil
JDP Reviews IABIED
AI is easy to control – AI Optimism
Velocity of money - Wikipedia
Notes on prosaic alignment and control | Rhys Gould
johnhw.github.io/umap_primes/index.md.html
Coasean Bargaining at Scale - Cosmos Institute
Conflict anxiety - by Chris Lakin - Locally Optimal
Agonism - Wikipedia
Why does training on insecure code make models broadly misaligned?
Scapegoating the Algorithm—Asterisk
The Worst Argument Against Ozempic - Cremieux Recueil
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge