Henry Hu
About
Work
Blog
Links
Reading
Links
Interesting reads I want to keep track of.
Why All Models Learn the Same Thing with Phillip Isola (MIT)
youtube.com
Watch @ 0:00
Genealogy
Algebra, Topology, Differential Calculus, and Optimization Theory for Computer Science and Machine Learning
cis.upenn.edu
Read
Genealogy
The World Inside Neural Networks
goodfire.ai
Read
Genealogy
Steering Along Manifolds to Control Neural Networks
goodfire.ai
Read
Genealogy
Six (and a half) intuitions for KL divergence
lesswrong.com
Read
Genealogy
A Comprehensive Mechanistic Interpretability Explainer & Glossary
dynalist.io
Genealogy
Toy Models of Superposition
arxiv.org
Read
Genealogy
How GPT, Claude, and Gemini are actually trained and served - Reiner Pope
youtube.com
Watch @ 0:00
Genealogy
Modular Manifolds
thinkingmachines.ai
Read
Genealogy
Six (and a half) intuitions for SVD
lesswrong.com
Read
Genealogy
Richard Dawkins is NOT Listening to Jordan Peterson - Bret Weinstein
youtube.com
Watch @ 0:14
Genealogy
Linear Mechanisms for Spatiotemporal Reasoning in Vision Language Models
arxiv.org
Read
Genealogy
Situational Awareness: From AGI to Superintelligence
situational-awareness.ai
Read
Genealogy
Universal Paperclips
decisionproblem.com
Genealogy
Phenomenology - Stanford Encyclopedia of Philosophy
plato.stanford.edu
Read
Genealogy
How Cursor Trained Composer on Fireworks: Distributed Infrastructure for High-Performance RL
youtube.com
Watch @ 0:00
Genealogy
Notes from the Underground
gutenberg.org
Read
Genealogy
The Brothers Karamazov
gutenberg.org
Read
Genealogy