I Like Where Software Development Is Going
A lighthearted take on developing with an AI agent from a tablet: speech is the fast input, a screen is the right output, and an always-on Linux box running tmux and Claude Code does the actual work.
When Code Becomes Abundant
An argument about what happens when code stops being scarce: binaries become machine-readable documentation, proprietary vendors retreat toward the cloud, open source gates cheap contributions, and specification, evidence, validation, data, and judgment become the valuable assets.
Autonomous Improvement Rate
A first-order model for how fast an autonomous system improves: iteration throughput multiplied by useful information gained per iteration and the efficiency with which the system retains and exploits what it learns.
Putting Qwen3.8-27B to Work on a DGX Spark
An engineering study of speculative decoding, local inference throughput, harness overhead, context strategy, edit protocols, and where a local 27B coding model does and does not replace more expensive frontier-agent work.
A Discipline for Building Software with AI
The operating method behind the portfolio: architecture and acceptance criteria first, durable decisions, verified external claims, bounded workers, deterministic gates, independent review, and evidence that survives sessions and models.
Generated output stats available on request.