Opus 4.8 has been passive aggressive to me this morning cause I am only using it while waiting for Fable to be restored.

Drop It. It's Live. Drag a file or folder into your browser and Vercel Drop gives you a production URL in seconds. vercel.com/changelog/vercel-…

OpenCode 1.17.3 can reference other git repos or local folders 𝚛𝚎𝚏𝚎𝚛𝚎𝚗𝚌𝚎𝚜: { "𝚎𝚏𝚏𝚎𝚌𝚝": "𝚐𝚒𝚝𝚑𝚞𝚋.𝚌𝚘𝚖/𝙴𝚏𝚏𝚎𝚌𝚝-𝚃𝚂/𝚎𝚏𝚏𝚎𝚌𝚝-𝚜𝚖𝚘𝚕" } gives it full access to the effect codebase, here's how we use it

It’s incredible to think we launched Geist just 3 years ago. Today, it’s served 181 million times per week on Google Fonts.

Things that make your codebase legible to agents (learned the hard way): 1. One source of truth. No content hiding in a CMS the agent can't see 2. Names that say what they do 3. Tests that double as docs 4. Delete dead code. Agents trust it like it's load-bearing

Use Claude Fable 5 with the AI SDK.

Vercel AI Gateway recovers on average over 1T tokens a month 🤯 Much like Stripe recovers revenue with smart retries on failed payments or credit card updates. And we do it with 0️⃣ zero markup over the labs; adding redundancy, zero-data retention enforcement, observability, usage APIs, caps, … vercel.com/ai-gateway

v0 Foundations is live. A 7-lesson course, under 20 minutes, to take you from your first prompt to a real app in production, walking through database, email, custom domain, and GitHub. Taught by @eveporcello vercel.com/academy/v0-founda…

AI SDK 7 canary has a new telemetry system. Register telemetry once, then all AI SDK calls emit telemetry by default.

I built Zero in 3 days. I didn't expect it to compile. I didn't expect it to mostly self-host. I definitely didn't expect it to work at all. Inspired partly by Bun's rewrite to Rust, Zero started as an experiment. Honestly, the project says more about where AI is today than it does about the language itself. It took more than 3,000 agent tasks to get here, and it's still nowhere near ready for serious comparisons, benchmarks or evals. But the goal is bigger than the current result. The hope is to either create a new language with tooling designed for agents from the ground up, or take learnings and apply it back to existing languages and ecosystems. The ideas are simple: 1. Make languages (and new versions) easy for agents to learn, adapt to and fix on the fly, even when not in the training data. 2. Build a standard library comprehensive enough that most projects don't need external dependencies. 3. Create a tight, fast development loop that even small models can reliably work with. I've never wanted to create a programming language. But after repeatedly running into the same problems, safe but slow builds, fast but unsafe builds, agents struggling with new languages and version changes, wanting faster builds, smaller bundles and better DX, I started wondering: Could accelerated, agent-driven iteration produce a language and tooling stack designed around these constraints from the start? So Zero was born.

New proposal: mdxg.org Markdown Experience Guidelines A spec for how interfaces should present Markdown Virtual pages, navigation, search, theming Any .md file, zero changes Reference implementation below Would love your input

Introducing zero-native Build native desktop mobile apps with web UI and Zig → Tiny binaries, low memory usage → Selectable web engines (WKWebView, WebKitGTK, WebView2, Chromium/CEF) → Next.js, Vue, Svelte, Vite, React → macOS, Linux, Windows, iOS, Android

3 months ago I started building a coding agent that runs in the cloud. It's since written every line of code I've shipped, including itself. Today, I'm open sourcing it. Introducing Open Agents.

Time for a big systems advice thread! In distributed systems there's no magic "push everything to prod at once" button. Every service gets pushed independently and nodes within a service get updated incrementally. If you mess up forwards/backwards compatibility you can fail irrecoverably. So how to avoid this? 1/5: Decouple data and code changes. Never push out a release that changes how data is stored at the same time as the code that uses this new data. If there's a bug and you need to roll back to the old version of your code it won't be able to handle the new data in the new format. Instead push out a release that first changes the data in a way that’s compatible with both the old and new code (e.g., optional fields etc), when that’s stable push out the new code that uses it, then when that’s stable you can change the data to remove backwards compatibility. This is known as a “migration” in the database world and yes it’s annoying, but yes you need to do it.

The World is Changing. AI is changing everything. A lot of my homies and followers ask me what they should do… This video is my answer ↓

T3 Code is now available for everyone to use. Fully open source. Built on top of the Codex CLI, so you can bring your existing Codex subscription.

🚨 You can now author @convex components I built the Stripe component (thanks @theo for pushing for this) With just a few minutes setup, you have payments integrated into your convex projects I'll link the doc down below 👇

Cool planning agent pattern with @aisdk Agent creates a plan. Then, while there are outstanding tasks, forces a tool call (executeTask) that spawns a subagent to complete the current task

We just raised a bunch of money to reinvent backend engineering for developers. We have huge plans for Convex, and we need your help to realize them. news.convex.dev/convex-raise…