Practical techniques for working with large language models.
Claude Code subagents used 2.6x to 5.9x the tokens of working sequentially, and were never faster. We measured the fan-out tax and the fixes.
We measured what Claude Code and OpenCode spend before reading your prompt, then added instruction files, MCP servers and subagents to the bill.
600 model calls across four frontier LLMs testing XML, Markdown, and JSON delimiters. Format usually does not matter. MiniMax M2.5 is the exception.
An open-source audit logging library for the EU AI Act. What it does, what it deliberately does not, and why that gap matters more than the code.
Article 12 is the most technically demanding obligation in the EU AI Act. Given a decision ID from six months ago, can you reconstruct the full chain?
Most engineering teams treat deployment as the finish line. Article 72 makes it a starting point. Post-market monitoring is a legal obligation.