Guillermo Rauch
Recent posts focus on AI & automation, events & community and product & building.
LinkedIn snapshot
Post performance
Likes + comments per post, last 6 months
Top posts
- 2mo agopostView →
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true: ○ You’re a beginner ○ Software is throwaway ○ You’re prototyping ○ You have no users / revenue ○ You’re tak…
♥ 3.3k💬 180↗ 1893.7k total - 1mo agopostView →
Anyone that works in AI is working the hardest they've ever worked in their lives. On the surface it's somewhat ironic (AI should give us back time!), but the reality is that it's the most fun, fascinating and empowering…
♥ 2.2k💬 171↗ 1152.5k total - 1mo agopostView →
Your software factory should be a monorepo. All your company context (design, marketing, sales, engineering, support…) in one place for agents to build upon. Turborepo is the build system for agentic coding: turborepo.d…
♥ 877💬 77↗ 34988 total - 1mo agoimageView →
I’ve been using fx.sh (a tiny, open, native coding agent from Vercel Labs) as my daily driver, and it’s a one-way street. It’s 10-20x smaller than the major coding CLIs. It starts up instantaneously. It feels more like…
♥ 798💬 39↗ 16853 total - 5d agopostView →
Security will become a larger and larger function in software companies. Security is verification engineering (eg: “my code is probably memory-safe”), as well as capital allocation (“what surface should I throw most toke…
♥ 745💬 78↗ 25848 total
Recent posts
All posts in the feed →- 2d agopostView →
One thing the engineering community will (re)discover is that every program can be ① hardened (edge cases squashed, inputs tightened, errors handled) and ② optimized (profiled, benchmarked, rewritten) basically ad infini…
♥ 15💬 1↗ 016 total - 4d agoimageView →
Introducing gdp-ts: Ghosts of Departed Proofs for TypeScript. gdp-ts is a library, linter and AI skill for safer API design. Under this contract, sensitive functions require 'proofs' that the caller performed an authori…
♥ 286💬 24↗ 6316 total - 4d agopostView →
DHH is fundamentally right about Rust. For context, Vercel has been undergoing a Rust-ification (carcinization, technically 🦀) for a while. One of the first projects we migrated was Turborepo, from Go to Rust¹. The mig…
♥ 577💬 79↗ 13669 total - 5d agopostView →
Security will become a larger and larger function in software companies. Security is verification engineering (eg: “my code is probably memory-safe”), as well as capital allocation (“what surface should I throw most toke…
♥ 745💬 78↗ 25848 total - 7d agoarticleView →
SvelteKit 3 is a wonder. Congrats to the team. So excited for Async Svelte & Remote Functions to cook. I built a tiny app, it built & deployed in 15 seconds end-to-end, it’s instant, and fx.sh + opus figured it all out…
♥ 138💬 11↗ 2151 total - 8d agopostView →
Most token aggregators have extreme noise from ① token promos from/to providers that train on your data or ② providers that *claim* to be ZDR. Vercel AI Gateway is the largest trustworthy datasource to understand global…
♥ 149💬 21↗ 8178 total - 10d agolinkedInVideoView →
AI SDK has hit 30M weekly downloads. One-shotted this video in fframes + fx.sh + opus. I asked 𝚏𝚡 to look at npm.bet/ai and highlight the 5M/10M/20M/30M milestones. Yes, this video was written in Rust and rendered on…
♥ 90💬 3↗ 7100 total - 11d agolinkedInVideoView →
I¹ ported my Mini web browser to Rust & Swift. It's faster, more secure, and shockingly, nicer to iterate on than Electron + Bun. I always wanted Safari-like UX but… Chrome 😁. Thanks to the 𝚌𝚎𝚏 crate, I can bundle u…
♥ 229💬 19↗ 8256 total - 15d agolinkedInVideoView →
Spend of OpenAI vs Anthropic vs Open (Vercel AI Gateway, last 2 months) • Anthropic still #1 in spend, but went 69% → 40% • OpenAI: 10% → 24% in spend • GPT-6 Astra + GPT 5.6 Sol are ripping • OpenAI now leads in token…
♥ 294💬 25↗ 15334 total - 15d agopostView →
ShellPerfBench. I'm really neurotic about the startup time of a new shell session. Opus 5.5 found a lot of really great optimizations other models missed. Anon, anytime you open a new terminal, you might be silently suff…
♥ 72💬 5↗ 178 total - 15d agoarticleView →
Muse, Instinct, OpenClaw, Claude Code… All successful agents have 3 key components: 🧠 Brain → model, harness (logic) 👐 Hands → tools, computer, browser 🗃️ Files → memories, skills, repos The 'easy' way is to throw…
♥ 283💬 24↗ 15322 total - 17d agolinkedInVideoView →
Love the tastefulness with which anthropic ships. Main reason I got excited about 'headless' for the web is that any given page could take whatever whimsical or unique shape you wanted. With AI, there's no excuse not t…
♥ 178💬 14↗ 1193 total - 17d agoimageView →
I'll be interviewing Tobias Lütke on stage at Vercel Ship SF on October 15. We'll be discussing agentic commerce, native rewrites, S3 WALs, slop grenades, and more 😂 Can't miss this convo with one of the all-time greats…
♥ 256💬 11↗ 2269 total - 18d agoimageView →
The thoroughness with which agents can test and QA software is unrivaled. I pointed out something wasn't rendering right in a mobile (in-app) browser. The thing goes to the depths of Mordor to reproduce, simulate, fix, d…
♥ 292💬 49↗ 10351 total - 20d agopostView →
The coolest thing about the recent wave of AI is that everyone is excited about building. All short-term drama aside, this is an immeasurably good development for the world. The people want to create and ship, not just…
♥ 630💬 38↗ 22690 total