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.
June 6, 2026
Copilot turned the meter on. The $20 tool was always a fiction.
On June 1, GitHub switched every Copilot plan to usage-based billing, and developers watched a single AI coding session eat a whole month's budget before lunch. The internet called it greed. It isn't — it's the meter finally being visible. Agentic AI was never a flat $20 a month; you just weren't shown the bill. Here's what that means for anyone building on these tools, and why cost has to be a design decision now, not a surprise.
- business
- agents
- ai-native
June 6, 2026
Three frontier models landed this month. I changed one line.
June 2026 is dropping three new frontier models in a single month — GPT-5.6, Gemini 3.5 Pro, and Claude Mythos — on top of two that shipped in May. For most teams that's a stressful treadmill of 'should we migrate?' For one that built the boring way, it's three free upgrades, each a one-line config change. The relentless model churn isn't a problem to keep up with. It's a gift you collect automatically — but only if you built the seam to catch it.
- ai-native
- architecture
- agents
June 6, 2026
Vibe coding ships the app and the breach with it
An AI social network called Moltbook launched in January; its founder bragged he 'didn't write a single line of code.' Three days later researchers found its entire database open to the world — 1.5 million auth tokens, 35,000 emails, private messages. It wasn't a freak accident. Studies keep finding that something like 45% of AI-generated code ships a known vulnerability. The demo is free now. The security review is the part you still can't vibe — and the bill for skipping it is somebody's data.
- security
- methodology
- ai-native
June 6, 2026
Your IDE isn't where you build anymore
Mistral just shipped a coding mode where you start a build from Slack, the agent works in a cloud sandbox while your laptop is off, and you get back a pull request to review. Cursor and others are doing the same. The editor — the thing we treated as the place where software gets made — is quietly becoming one trigger among many. The work is moving from keystrokes in a window to tasks you delegate and diffs you judge. That's a bigger shift in the job than it sounds.
- methodology
- ai-native
- agents
June 5, 2026
An agent in every laptop — and the end of the token bill
Everyone spent the spring panicking about the token bill. This week NVIDIA showed a structural answer arriving this fall: the agent moves onto your laptop. RTX Spark runs a 120-billion-parameter model with a million-token context locally — no per-token meter, your data never leaves the machine, and it's faster for the snappy stuff. It won't replace the frontier. But it quietly answers three of the year's biggest headaches at once.
- ai-native
- business
June 5, 2026
One federal AI standard over fifty states — what it means if you build
Yesterday a 269-page bipartisan bill dropped that could override every state's AI law, and the headlines are loud. If you build with AI, the useful question isn't the politics — it's whether this changes what you actually have to do. The honest answer: far less than the headline suggests, because the rules that bind your product were never the ones this bill touches. Here's the two-layer version, in plain terms.
- business
- ai-native