Machine Learning

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

Claude Code from Source: Architecture, patterns & internals of Anthropic's AI coding agent

Why your local LLM feels dumber than it is

Error by AI scribe during medical appointment leaves patient devastated

Everyone is building LLM routers, we deprecated ours

Kimi K3 Architecture Notes

GitHub - block/buzz: A hive mind communication platform

Nativ — Run AI locally on your Mac

Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver

PrismML — Concentrating intelligence

GitHub - jundot/omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the mac

GitHub - z-lab/paroquant: [ICLR 2026] ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference

Introduction to LLM Post-Training Techniques | PDF

I've been thinking a bit about continual learning recently, especially as it relates to long-running agents (and running a few toy experiments with MLX)

Unrolling the Codex agent loop

GitHub Projects Community (@GithubProjects) on X

RAGLight