Articles
In-depth research, comprehensive guides, and long-form thoughts on modern technology.
After Orthogonality: Virtue-Ethical Agency and AI Alignment
This essay argues that AI agents should adopt eudaimonic rationality, aligning with human practices rather than optimizing for rigid, consequentialist goals.
Designing High-Performance GPU Kernels With TileLang
This tutorial explores TileLang, a high-level Python domain-specific language for designing and compiling performance-oriented GPU kernels through TVM.
Open Dreamer Reproduces Dreamer 4 World Model Pipeline in JAX
Researchers released Open Dreamer, an open JAX and Flax implementation of the Dreamer 4 world model pipeline, complete with a full training recipe and demo.
Librarians Lead Viral Workshops Teaching People How to Avoid AI
Librarians across the country are hosting viral workshops teaching patrons how to disable unwanted AI features and reclaim autonomy over digital experiences.
One Cache Miss, Fifty Database Calls: Taming the Cache Stampede with HybridCache
A 99% cache hit rate won't save your database from a stampede. Here is how HybridCache in .NET prevents duplicate queries and protects your backend.
Quantization vs Distillation: Choosing the Right Model Compression Strategy
Quantization compresses a model's weights to lower precision. Distillation trains a smaller model to imitate the original. Here is how to choose between them.
Rauno's Field Notes #2: Designing Better Project Cards
Rauno shares design insights from iterating on project cards, including the value of tight information density and the challenges of widget design.
Generative AI and AI Product Moats
Cohere's observations on generative AI and product moats highlight the shift from model access to enterprise integration and data control.
Deep Neural Nets: 33 Years Ago and 33 Years From Now
A 2022 reproduction of a 1989 neural net reveals how little has changed in 33 years—and how much the next 33 years will transform the field.
MicroGPT: 200 Lines of Pure Python That Train a GPT
Andrej Karpathy's microGPT distills the entire GPT algorithm into 200 lines of pure Python. Here is how it works and what it reveals about LLMs.
Scaling Laws, Carefully: How Data Repetition and Fitting Choices Shape AI Performance
Scaling laws are a critical tool for predicting AI performance, but their clean form can be deceptive. New research shows that data repetition and subtle fitting choices can drastically change outcomes.
Harness Engineering for Self-Improvement: The Path to Recursive AI
Harness engineering is emerging as the key to AI self-improvement, moving beyond prompting to design the entire system that orchestrates, checks, and improves AI agents.