Articles
Notes, tests, and arguments.
A tutorial should do more than run, and an explanation should do more than agree with the first page of search results. These are my arguments about developer content, documentation, and the AI systems I build around them.
The Best LLMs for Coding in 2026: An Engineering Review
The best LLMs for coding on Real-SWE 1.1 (October 2026): the leaders, the cost per resolved task, open-weight options and a test for your own repo.
Model Context Protocol (MCP): Connecting AI Tools
Model Context Protocol (MCP) is the new standard for connecting AI models to data sources and tools. Here is why it matters, how it works, and why it is the missing link for agentic infrastructure.
Agent Harnesses: The Infrastructure Your LLM Agent Needs
Every production AI agent needs a harness. Here is what one contains, why frameworks often are not enough, and how to build the layer that actually determines reliability.
What Time to First Token (TTFT) Measures
Time to first token (TTFT) explained: what it measures, why reasoning models need time to first answer token, and how TTFT behaves under load.
Speculative Decoding: Speeding Up LLM Inference
Speculative decoding has a fast predictor draft tokens and the large model verify them in one pass. How it works, what it gains and when it stops helping.