

✓@vercel CEO



Actually a huge deal for web performance. 𝚊𝚐𝚎𝚗𝚝-𝚋𝚛𝚘𝚠𝚜𝚎𝚛 𝚟𝚒𝚝𝚊𝚕𝚜 is so smart… self-optimizing software is here!

OpenAI just put out the most cybersecurity-capable models in the world. Excellent timing. Important signal: @vercel DeepsecBench is a stealth cyber benchmark. No lab has had access to the codebases to train on. vercel.com/ai-gateway/leader…


My first commit to @nextjs was a spec. At the time I called it README-driven development. Before you w̶r̶i̶t̶e̶ generate code, define what you want. Prompt, spec, exit criteria, desired outcomes. The autonomy loop. github.com/vercel/next.js/co…


Own your intelligence roadmap: ① Use open SDKs & harnesses ② Own model choice with Gateways ③ Own your traces and data, enforce ZDR ④ Own your models with private inference

The old way: users are human, you run user interviews, get inspired, mock up user journeys. The new way: users are agents, you run evals, evals inform the software engineering loop. Good read on how we do evals at Vercel.

A new era of software is upon us. Personalized, fully owned, open source. And higher quality than what it replaces.

I believe Traces are the essential new primitive of software development and agentic evolution. Git changed the world by helping us collaborate around the delta unit of code. Traces are even more powerful than that. They capture the upstream intent, prompts, reasoning, skills and tools use. They are your intelligence. You should, of course, own and make full use of your intelligence. You start by securely capturing your traces. Then, set up the recursively self-improving systems based on the learnings they contain: friction, latency, outcomes. Excited to build this future with Tarun and team!

Introducing 𝚡𝚎𝚎𝚝: xeet-rs.vercel.app. A hermetic, pixel-perfect X post renderer in safe Rust / wasm. Zero browser, network, filesystem, system fonts. Renders a post to PNG in ~1ms (and 0.4 ms for @jack's "setting up my twttr" 😁). X is the global town square, and the medium is the message. Being able to preview what things will look like before posting is great for both humans and agents. Rendering with xeet is is 100x-1000x faster than booting up a browser and taking a screenshot, yet it's just as accurate. It reproduces Blink & HarfBuzz text shaping, 1/64px line breaking, RTL bidi, 28 Chirp font subsets, CJK/Math/Emoji fallbacks, "Show more" rules, etc. It's the kind of thing that would be wildly impractical, if not impossible, for a human engineer to pull off. Except 𝚡𝚎𝚎𝚝 is structured as an "autorepo." An oracle boots up Chrome, and verifies tens of thousands of text layout rules. A CI canary then watches the evolution of the original, and files signed PRs for agents to act on. It was conceived from the ground up around 'verification engineering', and the result speaks for itself. Enjoy!

AI models are getting really good at naming things. I created a little CLI to diagnose system slowdowns, and it named it 𝚑𝚘𝚐 🐖, which I love. Given they're already good at cache invalidation, maybe computer science's hardest problems are solved after all 😂


Got to experience the magic of @uisdk. Two prompts of fx + Gemini Argon. Pure Web Components. No framework. The agent reused 14 UI SDK behaviors out of the box 🤯: window resizing, drag, menubar hover-switching, typeahead, roving toolbar focus, 10-band EQ sliders, scoped hotkeys, ARIA, and WebMCP agent control. winamp-ui-sdk.vercel.app/ (source linked) Music by @suno.

Subagents on fx.sh work so well… extremely delightful. Amazing how much goodness fits in 6.33mb 😁 All my projects are built by planning with the smartest model + delegating to fast model subagents. It's a 1-line instruction in ~/.𝚏𝚡/𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍.