26 posts tagged with "ai"

This is my token telemetry for July 2026 — one developer's month, pulled from the Aliz AI usage dashboard. Earlier this month I wrote You Don't Deserve Fable (Yet), which argued that routing discipline comes before reaching for the biggest model on the menu. This post is a month of receipts for that argument, including the parts where I plainly haven't applied my own advice. It's also a mixture of before and after: the routing discipline was still forming while the month ran, so this isn't a steady state. Some of the chart describes habits I'd already changed, and some of it describes habits I was in the middle of changing.

Claude Fable is the most capable model Anthropic has shipped — above Opus class, frontier reasoning, genuinely impressive on hard problems. It's also the fastest way to burn through your token budget if you haven't built the discipline to use it correctly. Most developers will reach for it because it's the best, use it for tasks Haiku could handle, and wonder why their costs exploded. This post is about earning the right to use Fable by mastering the cheaper models first.

V0 is Vercel's AI-powered development platform that lets you generate, edit, and deploy full-stack web applications through natural language prompts. Since its launch as a UI component generator, it has evolved dramatically in the first half of 2026 — growing into a full-stack development environment with git integration, a terminal, merge conflict resolution, and enterprise features. What started as "generate a landing page from a prompt" now looks more like a cloud IDE competing with Cursor and Windsurf. This post traces the arc of that transformation and identifies the strategic bets Vercel is making.

You already use Zod to validate API responses. Now it's the contract layer between your app and LLMs. One schema gives you runtime validation, TypeScript inference, AND guaranteed structured output from GPT, Gemini, and Claude. Without it you're calling JSON.parse() on free text and praying the model didn't sneak in a markdown fence or an apologetic preamble.

AG-UI (Agent User Interaction Protocol) is an open, event-based protocol that standardizes how AI agents communicate with user-facing applications. Created by CopilotKit and adopted by Microsoft, Google, AWS, LangChain, and CrewAI, it fills the gap between MCP (agent↔tools) and A2A (agent↔agent) by defining the agent↔UI layer. It's MIT licensed with 14.4k GitHub stars and 50+ framework integrations.

AI coding tools are great at boilerplate, but they still hallucinate web API details, browser support, and even whether a feature exists at all. MDN's new MCP Server tackles that problem by letting MCP-compatible editors and agents pull current MDN documentation and browser compatibility data straight from the source.

TanStack AI reached beta on June 9, positioning itself as the "Switzerland of AI tooling" — framework-agnostic, provider-agnostic, and fully open-source with no hosted platform required. It's built by the same team behind React Query and TanStack Router, and it brings that same philosophy of composable, type-safe primitives to AI application development.

Since June 1, every Copilot token has a dollar sign attached. You're thinking about model selection, prompt size, and whether that 200-line file really needs to be in context. Good — but while you optimize your side, the VS Code team has been shipping infrastructure-level improvements that cut token consumption and latency without any user action. Ryan Caldwell and Bhavya U published a deep dive on these changes, and the numbers are worth knowing. The platform is doing heavy lifting so you can focus on the strategies you control.

The LLM Wiki pattern — previously just a gist from Karpathy and a growing community convention — now has a formal, versioned specification. On June 12, Google Cloud's Data Cloud team published OKF (Open Knowledge Format) v0.1, a vendor-neutral spec for representing curated knowledge for AI systems. This is the fourth post in our LLM Wiki series (previous posts: the pattern, our wiki mapping, local models), and arguably the most significant development since the idea first gained traction.

GitHub Copilot started as autocomplete for code. Then it became a chat assistant. Then a coding agent you could assign issues to. Now it's crossing the final threshold: an autonomous agent that runs on a schedule, without anyone prompting it. Copilot Automations turn your AI assistant into a background team member — one that shows up at 9am every day, does useful work, and opens a PR for review.