Notes
Short pieces about the methodology and architecture decisions behind the AI systems I ship — specs, evals, multi-agent orchestration, LLM integration, and the discipline of directing coding agents.
July 1, 2026
Voice agents just crossed the latency line
For years, AI voice agents failed on one thing: the pause. That half-second of dead air after you stopped talking made every phone bot feel broken. In 2026 the pause is gone — streaming speech end to end, new state-space voice models at 40ms, and sub-500ms round trips put voice inside the window where a conversation feels real. The model was never the hard part. Timing was — and timing is now an engineering problem, not a research one.
- ai-native
- agents
June 23, 2026
The best model didn't win. The default did.
ChatGPT just fell below 50% of the AI assistant market for the first time — down from 65% a year and a half ago. Gemini is surging, and the biggest reason isn't that it's smarter. It's that Gemini is the default, built into Android and Google Workspace. For anyone building AI products, that's the lesson: distribution beats the model, almost every time.
- ai-native
- business
June 23, 2026
The tool you build on just got bought
SpaceX is buying Cursor — the AI coding tool a lot of teams now live in — for $60 billion in stock, days after the largest IPO in history. It's the biggest-ever acquisition of a venture-backed startup. The lesson for builders isn't the price tag. It's that the tool under your whole workflow can change owners overnight, and you should be ready for that.
- business
- ai-native
June 19, 2026
Apple made the model a setting
At WWDC this month Apple rebuilt Siri on Google's Gemini — and then let you swap in Claude or ChatGPT instead. The most vertically integrated company on earth just turned the AI model into a dropdown menu. That's the clearest signal yet that the model is a replaceable part, not a moat — and it's exactly how you should be building too.
- architecture
- ai-native
June 19, 2026
Search stopped sending you traffic
Google's AI Mode now answers in the page on Gemini 3.5 Flash, and the clicks are vanishing: one study found people click a link on only about 8% of visits where there's an AI answer, versus roughly 15% without. Ranking number one means little if nobody clicks through. The game is shifting from ranking on the page to being the source the answer is built from.
- ai-native
- business
June 19, 2026
The bottleneck moved to the power grid
OpenAI lined up 10 gigawatts with NVIDIA and 6 more with AMD; a Stargate data center just got 1.4 gigawatts approved in Michigan over furious local objections. The constraint on AI stopped being the model a while ago. It's electricity, land, and the politics around them. That reframes what efficiency is worth — and it's the same lesson that governs systems much smaller than a data center.
- architecture
- ai-native