Ai
Where I run my coding agents, and why it depends on the box
How I limit coding-agent blast radius: disposable Dell micros for unattended work, with permissions kept on around valuable credentials. read more →
Why local models get stuck repeating JSON
A faster GPU turned 'too slow' into 'broken': why grammar-constrained JSON extraction sends local vision models into repetition loops, and what helps. read more →
Pydantic AI structured outputs and evals on Bedrock
How I stage model trust on Bedrock: structured outputs to lock the shape, Pydantic Evals for content, and a calibrated LLM judge for the open text. read more →
Skills or MCP servers: when you need a server
Skills can drive any CLI, but your laptop's credentials aren't an access model. Once data is shared and access has to be governed, you need an MCP server. read more →
Anchoring specs to code with ast-grep
I use ast-grep rules to keep living specs tied to the code they describe, even when files move and line numbers change. read more →
The shapeshifting engineer
AI writes most of the code now. The engineering job is moving towards judgement, better specs, and checking what the machine produced. read more →
Local models in mid-2026: the engineering that closed the gap
How open weights got close enough to run at home in 2026, the engineering that got them there, and why a memory crunch made the box pricier. read more →