机器学习
Moving To Substack
I’m freezing this blog and starting to post on my Substack instead. The authorin…
Remaking Old Computer Graphics With AI Image Generation
Can AI Image generation tools make re-imagined, higher-resolution versions of ol…
Applying massive language models in the real world with Cohere
A little less than a year ago, I joined the awesome Cohere team. The company tra…
Understanding Convolutions on Graphs
Understanding the building blocks and design choices of graph neural networks.…
Distill Hiatus
After five years, Distill will be taking a break.…
Weight Banding
Weights in the final layer of common visual models appear as horizontal bands. W…
Controlling Reasoning Effort in LLMs
How LLMs Learn Low-, Medium-, and High-Effort Reasoning Modes…
.webp)
LLM Research Papers: The 2026 List (January to May)
A curated roundup of notable LLM research papers that came out this year…
My Workflow for Understanding LLM Architectures
A learning-oriented workflow for understanding new open-weight model releases…
Harness Engineering for Self-Improvement
The concept of recursive self-improvement (RSI) dates back to I. J. Good (196…
Why We Think
Special thanks to John Schulman for a lot of super valuable feedback and direc…
Extrinsic Hallucinations in LLMs
Hallucination in large language models usually refers to the model generating un…
Generative AI and AI Product Moats
Here are eight observations I’ve shared recently on the Cohere blog and videos t…
The Illustrated Stable Diffusion
Translations: Chinese, Vietnamese. (V2 Nov 2022: Updated images for more precise…
The Illustrated Retrieval Transformer
Discussion: Discussion Thread for comments, corrections, or any feedback. Transl…
A Gentle Introduction to Graph Neural Networks
What components are needed for building learning algorithms that leverage the st…
Adversarial Reprogramming of Neural Cellular Automata
Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.…
Branch Specialization
When a neural network layer is divided into multiple branches, neurons self-orga…
Using Local Coding Agents
Using Open-Weight Models in Local Coding Harnesses as an Alternative to Claude C…
Recent Developments in LLM Architectures: KV Sharing, mHC, and Compressed Attention
From Gemma 4 to DeepSeek V4, How New Open-Weight LLMs Are Reducing Long-Context …
Components of A Coding Agent
How coding agents use tools, memory, and repo context to make LLMs work better i…
Scaling Laws, Carefully
Scaling laws are one of the most critical empirical findings in deep learning. T…
Reward Hacking in Reinforcement Learning
Reward hacking occurs when a reinforcement learning (RL) agent exploits flaw…
Diffusion Models for Video Generation
Diffusion models have demonstrated strong results on image synthesis in past ye…