Why we built our LLM workflow runtime in Go instead of Python

GPU Memory Math for LLMs: Formula That Tells You What Fits on Your GPU

Advanced Quantization Algorithm for LLMs

Repowise: a deterministic, zero-LLM code health scorer for Go, tested against Hugo's actual bug history

omlx: LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Show HN: A tiny C program where an LLM rewires its DAG while running

Applying LZ77-style sequence compression and LZW substitution to LLM context reduction

How LLMs Work, Part 1: How LLMs Process Text

Getting LLMs Drunk to Find Remote Linux Kernel OOB Writes (and More)

How I Added an LLM-Based Grammar Checking + TeX Math Import To LibreOffice