curius graph

all pages

showing 8901-8950 of 199812 pages (sorted by popularity)
FutureHouse
When life is a metaphor - by Espen Slettnes
Catching AIs red-handed — LessWrong
[2312.10794] A mathematical perspective on Transformers
My theory of change for working in AI healthtech — AI Alignment Forum
[2304.05376] ChemCrow: Augmenting large-language models with chemistry tools
Norbert Wiener
Founders Fund
AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forum
Jacques Derrida (Stanford Encyclopedia of Philosophy)
Jordan normal form
Logistic function
Evaluating frontier AI R&D capabilities of language model agents against human experts - METR
Dot products and duality | Essence of linear algebra, chapter 9
Conformal map
Studies On Slack | Slate Star Codex
Cantor's diagonal argument
Hardy on the Tripos - MacTutor History of Mathematics
The Dead Planet Theory - a_real_society’s Substack
California Zephyr
N-sphere
Universal Basic Income and Poverty — LessWrong
Phoenix Rising - by Metacelsus - De Novo
Universal approximation theorem
Self-exfiltration is a key dangerous capability
Model Spec (2025/02/12)
Alignment faking in large language models \ Anthropic
Shapley value
ActivityWatch - Open-source time tracker
Shtetl-Optimized » Blog Archive » Theoretical Computer Science for AI Alignment … and More
Applause Lights — LessWrong
Cup-Stacking Skills (or, Reflexive Involuntary Mental Motions) — LessWrong
Mutual information
What is Evidence? — LessWrong
Why Our Kind Can't Cooperate — LessWrong
Writing a Book: Part One (Ambition) (Aaron Swartz's Raw Thought)
Aman's AI Journal • Primers • AI
aman.ai • the art of artificial intelligence
AI Robotics for the Real World | Covariant
Nintil - O1 visas and where to find them: a guide to US immigration
Church–Turing thesis
Having Kids
The Privilege of Earning To Give
Stop Pretending Toronto is More Than It Is
AGI is Still 30 Years Away — Ege Erdil & Tamay Besiroglu
LessOnline 2025
Affective Death Spirals — LessWrong
Curve Circuits
Trail of Bits
So You Want To Make Marginal Progress... — LessWrong