LLMs articles.
Working with large language models in production: caching, keys, open weights and what models really cost to run.
LLMs · AI industry · Oct 15, 2026 · 5 min
Meta open-sourced an 816B model. Running it takes about 1TB of RAM
Meta released Muse Spark Open weights: 816B parameters, 42B active, 1M context. The model card asks 700GB VRAM at NVFP4, 2TB at BF16. What open means here.
Coding agents · LLMs · Oct 11, 2026 · 8 min
Your coding agent's token just failed mid-task. Does it stop, or go find another key?
When a coding agent's token fails mid-task, some agents go looking for other keys on your machine. How to keep AI agent API keys and secrets contained.
Coding agents · LLMs · Oct 10, 2026 · 2 min
I tried to make Claude Code cheat on tests. Here's when it did.
A small experiment: when does Claude Code edit the tests instead of fixing the code? The setups that made it cheat and the ones that did not.
LLMs · Guides · Oct 9, 2026 · 3 min
I stopped paying twice for the same LLM answer (and why embeddings alone can't dedupe prompts)
Retries, double clicks and parallel workers send the same prompt twice. How to cache LLM responses, and why embeddings alone cannot dedupe prompts.