Software Engineer & AI Enthusiast
For decades, 'free software' and 'open source' were nearly synonymous — because building something worth sharing required a community. AI has dissolved that constraint. But the story isn't that open source is dying. It's that open source used to do five jobs at once, and AI is separating those threads. Some become less necessary. Others become more critical than ever.
Polyphon is a desktop app I shipped this week for orchestrating multiple AI models in a single conversation. Instead of tab-juggling between Claude, GPT, and Gemini, you run all of them as voices in one shared session where they can actually read and respond to each other. Here's why I built it, what technical bets I made, and what I learned on launch day.
This blog runs on a custom automation pipeline where AI agents compete, critique, and synthesize every post. Here's how the /create-blog-post command, a DALL-E 3 image generation script, pre-commit image enforcement, and WebP optimization all compose into a content system that behaves like production software.
Read more
AI agents can write code, fix bugs, and ship features — but who can be trusted to ship production software when most implementation is delegated? Meet the Agent Wrangler: the engineer who decomposes work, directs multiple agents, validates output, and owns the outcome. Deep technical foundations matter more than ever. The keyboard gets less important. Judgment gets everything.
After refusing to pay for yet another AI subscription I couldn't customize, I switched from Notion to Obsidian and discovered there was no way to use my existing AI services inside it. So I built one — an open source AI Agent Sidebar plugin developed with agentic engineering and the dark factory method.
The first version of agent-config tried to impose uniform rules on Claude, Codex, Copilot, and Gemini — and it broke. The fix wasn't better engineering up front. It was accepting failure fast, letting AI handle per-agent format conversion, and shipping a v2 that actually works. Here's what the failure taught about human instinct, AI-assisted iteration, and why failing cheaper is a skill worth building.
Between Claude Pro, ChatGPT Plus, GitHub Copilot, Cursor, and a handful of specialty tools, a serious AI stack can run $100 or more per month. This post explores a practical closed-loop strategy: give every subscription a job, pick one small revenue experiment, and use the tools themselves to generate enough income to cover the bill.
As AI features proliferate across SaaS products, customers are waking up to a frustrating reality: they're paying for the same AI capabilities multiple times. The Bring Your Own Key (BYOK) model — letting users connect their own Anthropic, OpenAI, or Gemini API keys — is the market's answer. This post unpacks the real tradeoffs on both sides and maps out which model fits which kind of user.
Attractor is a DOT-based AI pipeline orchestration engine that borrows its name and philosophy from dynamical systems theory. Define your workflow as a Graphviz directed graph, and Attractor pulls multi-LLM execution toward your desired outcome — through conditional branches, retries, human gates, and failure recovery. The entire codebase is AI-generated, making it a live proof of the Software Factory paradigm it embodies.
Understanding how large language models actually work under the hood removes some of the wonder — but it also replaces irrational fear with informed clarity. AI isn't magic, it isn't plotting against us, and knowing why might just change how you think about your own brain.
Read more