irrationalfab

Agreed. It is ironic that in the AI race, the real differentiation may not come from how smart the model is, but from who builds the best application layer on top of it. And that application layer is built with the same kind of software these models are supposed to commoditize.

Interesting! Generating PDFs with properly paginated content is still a pain point in 2026.

Do you have a comprehensive integration test suite that can validate the robustness of your implementation?

Prince starts at 2k. This is OSS

Handy is genuinely great and it supports Parakeet V3. It’s starting to change how I "type" on my computer.

Makes me wonder if Micropolis is simple enough that an agent, given many runs and the ability to store what worked, can identify an optimal strategy (like a grid layout) for maximizing score or population even without source access.

+1... like with a large enough engineering team, this is ultimately a guardrails problem, which in my experience with agentic coding it’s very solvable, at least in certain domains.

Agent/MCP/Skills might be "Netscape-y" in the sense that today's formats will evolve fast. But Netscape still mattered: it lost the market, not the ideas. The patterns survived (JavaScript, cookies, SSL/TLS, progressive rendering) and became best practices we take for granted.

The durable pattern here isn't a specific file format. It's on-demand capability discovery: a small index with concise metadata so the model can find what's available, then pull details only when needed. That's a real improvement over tool calling and MCP's "preload all tools up front" approach, and it mirrors how humans work. Even as models bake more know-how into their weights, novel capabilities will always be created faster than retraining cycles. And even if context becomes unlimited, preloading everything up front remains wasteful when most of it is irrelevant to the task at hand.

So even if "Skills" gets replaced, discoverability and progressive disclosure likely survive.

> If those features aren't supported by the widget's hard-coded schema, you're out of luck as a user.

Chat paired to the pre-built and on-demand widgets address this limitation.

For example, in the keynote demo, they showed how the chat interface lets you perform advanced filtering that pulls together information from multiple sources, like filtering only Zillow housers near a dog park.

This feels like the death of the app, and the rise of the micro-app.

Very interesting tech. Ephemeral, high-fidelity preview environments that require zero setup are a key enabler. They let you rapidly validate changes within the complete context of a web or mobile app, accelerating feedback loops and cutting friction for minor updates. This also empowers business users to safely implement small, self-contained UI adjustments which is particularly powerful when combined with LLM-driven suggestions.

This nails a real problem. Non-trivial PRs need two passes: first grok the entrypoints and touched files to grasp the conceptual change and review order, then dive into each block of changes with context.

Like convex.dev