Guillermo Rauch retweeted
Our engineers have been fanboying over this episode with Vercel founder @rauchg all week.
I asked him how he’s built this much loyalty and trust with developers.
“Trust is gonna be one of the most valuable moats for a post-AGI business.”
But he says “trust is an output, not an input.”
Meetups and any tactic you can point to “probably ain’t it.”
What earns it is the unglamorous work: security, fixing bugs, simplicity, great documentation.
This week on Library of Minds, the legend Guillermo Rauch joins us to talk about competing with AWS, selling to agents, building verification loops for agent evals, deciding which SaaS tools to replace, and raising his “six sub-agents” (his kids) in an AI world.
0:39 - How to Compete With a Giant (AWS)
5:38 - One Person Doing the Work of Thousands
17:15 - Trust Is the Moat After AGI
24:24 - You’re Not Confronting Enough Pain
25:54 - His Slack Channel Called “Scream”
27:46 - Your Next Customer Is an Agent
30:05 - How to Sell to Agents
37:05 - The Future Is Just Capital Allocation
47:30 - The Night His House Caught Fire
49:50 - Raising Six Sub-Agents (His Kids)
Guillermo Rauch retweeted
Vercel × @ElevenLabs: 14 models on AI Gateway, 50% off through Nov 9.
• Realtime voice agents
• Music
• Sound effects
• Multi-voice dialogue
• Streaming speech over WebSockets
• Speech to text
vercel.com/blog/elevenlabs-o…
Guillermo Rauch retweeted
UI and math time! UI = f(props) is the most famous line in React. But that f is JavaScript, not math.
Inspired by @_chenglou’s Handwired project, I compiled a <Dashboard/> component into a real math function, and asked what becomes possible.
calculus-of-interfaces.verce…
Guillermo Rauch retweeted
Incredible work
the beauty of the new @vercel & @Shopify partnership, you can add some whimsy back to the web.
KidSuper x DC Super-Villans Out Now!
DCSV.KIDSUPER.COM
Guillermo Rauch retweeted
Speaking of security, we created a registry for building OIDC configuration components.
Pick your providers, form and validation libraries, and token verifier (powered by jose). Then run one command to copy everything into your app.
I've built these a few times before. I know how annoying they can be to get right. Hope this helps.
ui.shadcn.com/oidc
It's time to retire long-lived static credentials.
We surveyed 1,000+ SaaS vendors and found only 8.4% support secure auth. This is our call to action and how we're doing our part.
vercel.com/blog/death-to-lon…
Guillermo Rauch retweeted
I benchmarked scriptc.dev against bun --aot
scriptc is 1.6x faster than bun --aot
Should you trust this benchmark? Nope. You should never trust benchmarks, but especially not this one, because it is the one that scriptc was optimized against and it does not benchmark *your* app nor does it benchmark any *real* app. Of course, you all already understand that this is true for all benchmarks you've seen here and are consequently very calm and rational about it.
big draft pr
github.com/oven-sh/bun/pull/…
Guillermo Rauch retweeted
Happy Ship Day
⢿⣶⡀⠀⢰⣿⠿⢿⠿⢿⠿⢿⣿⣿⡆⠀⢀⣶⡿
⠀⠙⢿⣦⢸⣿⣤⣼⣤⣼⣤⣼⣿⣿⡇⣴⡿⠋
⠀⠀⠀⠉⢸⡏⠉⢉⡉⠉⢉⡉⠉⢹⡇⠉
⠀⠀⠀⠀⢸⡇⠀⢸⡇⠀⢸⡇⠀⢸⡇
⠀⠀⠀⠀⢸⡇⠀⠈⠁⠀⠈⠁⠀⢸⡇
⠀⠀⠀⠀⠸⣧⣤⣤⣤⣤⣤⣤⣤⣼⠇
⠀⠀⠀⠀⠀⠀⠰⣾⡇⠀⢸⣷⠆
Guillermo Rauch retweeted
Engineers at @RogoAI build the company's internal apps on Vercel. They deployed over 73,000 times last month.
Coding agents ship to production in 5 minutes, and run everything from churn risk analysis to the sales team's deal desk.
vercel.com/blog/how-rogo-shi…
Guillermo Rauch retweeted
Jev is now available on the @vercel AI Gateway vercel.com/ai-gateway/models…
Guillermo Rauch retweeted
Given the state of AI we must internalize: Everything hackable will get hacked.
Two forces are at work:
▪︎ Near-frontier open weight models hack without refusal
▪︎ Frontier models help you defend yourself
How we're approaching this new reality ↓
vercel.com/blog/everything-h…
Guillermo Rauch retweeted
YES-CODE
An entire category of software, "no-code", was built under the presumption that code is expensive, difficult, and scarce.
Coding agents have forever changed the equation. Code is now cheap, easy, and abundant.
I remember @cramforce being asked by an analyst long ago: "soo, is @vercel like a no-code platform?" Without hesitation he goes "no, it's the absolute opposite. It's a yes-code platform." 😁
A key thing we set out to do was to be uncompromising in quality and sophistication of the things you could host. No-code solutions took shortcuts and set hard ceilings, typically on performance and sophistication.
Our mission is to create the easiest cloud for agents that you never graduate from.
PS: welcome warp.dev to Vercel!
Guillermo Rauch retweeted
After developing the app locally (two prompts), deploying it took one prompt:
> Push this to Vercel. Use Stripe Projects to create the account. Store the state somewhere safe.
Claude chose to use Upstash as its datastore, which seems to be working well.
Guillermo Rauch retweeted
After a month of Grok 4.5, Next.js, and the Vercel labs stack, I can say without a doubt it's my favorite web stack of all time
I'm using all of the 16.3 recommendations, all Vercel skills, portless, and agent browser. Nothing else
This stack solves every problem I had in the past. No port conflicts, seamless browser testing and debugging and it's fast af with Grok 4.5
Next is tracking evals here. Imo nothing beats Grok because of its speed
nextjs.org/evals
Guillermo Rauch retweeted
Available now on next@preview! (16.3.0-preview.9)
Fable just found a 15-30% memory efficiency improvement in Turbopack / Next.js, nearly autonomously.
@tobi asked me today: what have been your “holy s***” moments with AI?
My answer was: it’s every single week. And it’s accelerating. In fact, “WTFs/day” might just be my favorite metric for AI progress.
It’s one thing to read benchmarks or stories online. It’s another to watch these machines pull engineering feats every day.
3 days ago? Sol helped us find novel vulnerabilities in some of the most audited code in the world. Today? Fable helps us ship this large optimization of a very complex Rust codebase. I just saw some results of work we’ve done to shrink binaries by 10-20x. List goes on.
Guillermo Rauch retweeted
Sol for developing next.js:
We've been testing GPT-5.6-Sol for over 2 months now. It’s incredibly good in my day-to-day working on Next.js.
It understands architecture tradeoffs. It can investigate complicated Next.js issue reports. It considers other areas of the codebase when fixing bugs. Needs very little guidance. Short prompts are enough.
There’s some big refactors of the Next.js server that it implemented end-to-end with me pointing at high level possible improvements (we have skills for how to grab our failing test suites on PRs, deployment tests, etc.)
Those PRs are ready to merge after Next.js 16.3 has been released.