James Arthur

A small ship I love: We made Claude.ai and our desktop apps meaningful faster this week. We moved our architecture from SSR to a static @vite_js & @tan_stack router setup that we can serve straight from workers at the edge. Time to first byte is down 65% at p75, prompts show up 50% sooner, navigation is snappier. We're not done (not even close!) but we care and we'll keep chipping away. Aiming to make Claude a little better every day.

Introducing the @Tan_Stack Intent Skills Registry Intent may use NPM as it's *distribution* registry (awesome), but finding/browsing skills in a sea of NPM modules definitely deserves it's own UI/service - Mirrored from NPM - Package/Skill Search - History/Changelogs Coming soon: - API/CLI for search/lookup - Cross discovery for non-intent skills 🔗⬇️🧵

x.com/i/article/2030…

The next step for autoresearch is that it has to be asynchronously massively collaborative for agents (think: SETI@home style). The goal is not to emulate a single PhD student, it's to emulate a research community of them. Current code synchronously grows a single thread of commits in a particular research direction. But the original repo is more of a seed, from which could sprout commits contributed by agents on all kinds of different research directions or for different compute platforms. Git(Hub) is *almost* but not really suited for this. It has a softly built in assumption of one "master" branch, which temporarily forks off into PRs just to merge back a bit later. I tried to prototype something super lightweight that could have a flavor of this, e.g. just a Discussion, written by my agent as a summary of its overnight run: github.com/karpathy/autor… Alternatively, a PR has the benefit of exact commits: github.com/karpathy/autor… but you'd never want to actually merge it... You'd just want to "adopt" and accumulate branches of commits. But even in this lightweight way, you could ask your agent to first read the Discussions/PRs using GitHub CLI for inspiration, and after its research is done, contribute a little "paper" of findings back. I'm not actually exactly sure what this should look like, but it's a big idea that is more general than just the autoresearch repo specifically. Agents can in principle easily juggle and collaborate on thousands of commits across arbitrary branch structures. Existing abstractions will accumulate stress as intelligence, attention and tenacity cease to be bottlenecks.

Yesterday was a blast! We had an awesome panel discussion on the future of web dev stack, followed by live demos by @WaspLang, @ElectricSQL, @modelence, and @beonauto. Thanks everybody for coming!

I know I haven't been tweeting a lot about Hazel lately but I have been quietly cooking 👀 Currently redesigning some of the BotSDK with durable streams from the @ElectricSQL team to make it even easier and more reliable to build custom bots in Hazel Desktop App first stable release is coming very soon Mobile App is not far off And lastly the first stable 1.0 release of Hazel will be coming very very soon with a build in two way sync for all your Slack Channels and Users to make migrations super easy. So excited to finally ship all of it soon

You asked for TanStack skills, we built the whole pipeline. Introducing @tan_stack Intent (alpha) 📦 Ship agent-readable "skills" inside npm packages 🔍 Auto-discovered from node_modules 🔄 Knowledge sync with npm update 📂 Distributed - skills live in library repo 🧩 Composable - mix core + framework-specific skills 🌐 npm, pnpm, bun, yarn, deno No stale training data. Just npm install! 🔗 ⬇️🧵

You asked for TanStack skills, we built the whole pipeline. Introducing @tan_stack Intent (alpha) 📦 Ship agent-readable "skills" inside npm packages 🔍 Auto-discovered from node_modules 🔄 Knowledge sync with npm update 📂 Distributed - skills live in library repo 🧩 Composable - mix core + framework-specific skills 🌐 npm, pnpm, bun, yarn, deno No stale training data. Just npm install! 🔗 ⬇️🧵