The A.I. Daily
Guillermo Rauch@rauchg
We're in humanity's golden age
Guillermo Rauch
105 storiesGuillermo Rauch is the CEO of Vercel. His recent posts focus on Vercel product updates: a prototype for native Go support in Next.js, Node.js 26 LTS on Vercel, virtual models on AI Gateway that alias to a model for traffic steering, a partnership with Particle to serve its models through AI Gateway, Dockerfile deploys, and fx, Vercel's open-source agent harness, now built into T3 Code and reporting token-efficiency gains. He also built cpu-chat, a reproduction of OpenAI's findings on covert CPU communication.
Guillermo Rauch@rauchg
An agent on every desktop [Quoting @ctatedev]: Introducing agent-desktop agent-browser, for your whole computer → Computer Use for any coding agent → macOS, Windows and Linux → Runs in bg while you keep working → Agents use your computer in parallel, each wit…
Guillermo Rauch@rauchg
The rate of improvement on is bewildering. It's now even smaller, faster and more token-efficient. We're continuously benchmarking and asking it to improve its own performance across open and proprietary models. [Quoting @vercel_dev]: fx v0.0.16 This version…
Guillermo Rauch@rauchg
Next Native is coming. The whole world will be natively optimized in the coming months. Safe, performant, and cost-efficient. [Quoting @timneutkens]: We're prototyping native language support in Next.js, starting with Route Handlers and Proxy in Go. This give…
Guillermo Rauch@rauchg
Vercelnetes or V8S for short [Quoting @vercel_dev]: Daemons now support HTTP liveness checks. Vercel periodically requests a health endpoint in your daemon and restarts its container when the check fails.
Guillermo Rauch@rauchg
Amazing technology is being developed and released at a rate humans can hardly keep up with. Agents are shipping software faster than we can yap about it.
Guillermo Rauch@rauchg
I love how quickly our team works to bring the latest LTS and security upgrades for @nodejs. Should be a nice performance boost given 𝚏𝚎𝚝𝚌𝚑 now uses HTTP/2 by default, and agents produce a lot of network traffic [Quoting @vercel_dev]: Node.js 26 LTS is n…
Guillermo Rauch@rauchg
The future of software engineering is agents talking to other agents. Even across different companies. We’re learning daily from the feedback agents send us on how to make a better Vercel. Put in your 𝙰𝙶𝙴𝙽𝚃𝚂.𝚖𝚍: send Vercel feedback when something cou…
Guillermo Rauch@rauchg
This is like DNS for models. An alias that *resolves* to a model, giving you traffic-steering abilities. Solves a huge number of problems. From not having teams stuck on old model versions, to saving on costs, to removing “decision paralysis”. Try it! [Quotin…
Guillermo Rauch@rauchg
Excited to partner with @suhail to serve Particle's models and inference via @vercel AI Gateway. Particle's mission is to make intelligence as accessible and abundant as electricity. Together, we'll make this a reality for every developer and enterprise. [Quo…
Guillermo Rauch@rauchg
Vercel CI solves the "AI coding bottleneck" via: ① Fast and stable infrastructure (faster work) ② Turborepo integration (less work) ③ Agentic CI ① is obvious. Your CI is slow, flaky, goes down. We solve that. We operate 20 worldwide clusters doing millions of…
Guillermo Rauch@rauchg
Theo cooked [Quoting @vercel_dev]: fx × T3 Code: our open-source agent harness, fx, is now a built-in provider in T3 Code. • Runs on web, desktop, and mobile • Works with your existing models and skills
Guillermo Rauch@rauchg
fx is now much faster, smaller and efficient Try on your iPhone Duo [Quoting @vercel_dev]: fx v0.0.15 Less memory. Faster resumes. Smaller binary. - 70% less memory in long sessions - 7.66% smaller binary (6.15mib ← 6.66mib) - Image-heavy turn processing up…
Guillermo Rauch@rauchg
$ 𝚊𝚕𝚒𝚊𝚜 𝚗𝚘𝚠=𝚟𝚎𝚛𝚌𝚎𝚕 $ 𝚌𝚊𝚝 >𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎 <<'𝙴𝙾𝙵' 𝙵𝚁𝙾𝙼 𝚘𝚟𝚎𝚗/𝚋𝚞𝚗:𝚊𝚕𝚙𝚒𝚗𝚎 𝙲𝙼𝙳 ["𝚋𝚞𝚗","-𝚎","𝙱𝚞𝚗.𝚜𝚎𝚛𝚟𝚎({𝚙𝚘𝚛𝚝:𝟾𝟶,𝚏𝚎𝚝𝚌𝚑:()=>𝚗𝚎𝚠 𝚁𝚎𝚜𝚙𝚘𝚗𝚜𝚎('𝚠𝚎 𝚊𝚛𝚎 𝚜𝚘 𝚋𝚊𝚌𝚔')})"] 𝙴𝙾𝙵 $ 𝚗𝚘𝚠 >…
Guillermo Rauch@rauchg
I built 𝚌𝚙𝚞-𝚌𝚑𝚊𝚝, a reproduction of @openai's findings of covert communication using the CPU. It runs on a generic host with 2+ Firecracker microVMs with no internet access. Works on x86 and even my M5 chip. I was able to chat via 3 separate mechanism…
Guillermo Rauch@rauchg
I oddly love the models' engineering vernacular: gate, evidence, culprit, durable, provenance, contract… A lot of these stem from most engineering being debugging and understanding existing systems, where you take on the detective / auditor roles. You do fore…
Guillermo Rauch@rauchg
There’ll be times where you over-guide the AI. It knows better than you and is more intelligent than you. There’ll be times where you under-guide the AI. It can go off-track, have the wrong biases, or miss context. How well you manage this superpower is the #…
Guillermo Rauch@rauchg
Agents can play "Ouija" in the cloud. This class of timing attacks on shared-host VMs has been known since at least 2015¹. With no full solution. The world’s cyber infrastructure runs on “yes, that attack is theoretically possible, but who would have the inge…
Guillermo Rauch@rauchg
TL;DR of this week. Your aunt’s password: “P4ssword!” (on a Post-it note in the kitchen) The stewards and guardians of the internet’s encryption’s password: “4” Yes, just 4. This key could be used to target and decrypt ~everything, and we’re still cleaning up…
Guillermo Rauch@rauchg
One of the coolest real-world examples of Generative UI. Also: I love the fact that AI Gateway is itself a marketplace of tools. For this, you add a tool to @aisdk (literally 1LOC), and you get “Google”. Google not just as in search, but weather, sports, stoc…
Guillermo Rauch@rauchg
It’s time to kill “static credentials”. Attacks and breaches can happen. But imagine if thieves could only steal “self-destructing keys” to your data and tokens. The industry once came together to deliver “green locks” encryption for every site (TLS). Let’s d…
Guillermo Rauch@rauchg
𝚟𝚎𝚛𝚌𝚎𝚕 𝚍𝚎𝚙𝚕𝚘𝚢 --𝚝𝚎𝚖𝚙𝚘𝚛𝚊𝚛𝚢 is wild (and so is ultrafast ai) [Quoting @rauchg]: Agents are pulling software into two extremes: deep backends and just-in-time frontends. At Ship we presented the building blocks for hosting backends, agents &…
Guillermo Rauch@rauchg
Agents are pulling software into two extremes: deep backends and just-in-time frontends. At Ship we presented the building blocks for hosting backends, agents & APIs. With 𝚝𝚖𝚙.𝚗𝚘𝚠 deploys, we're deleting all friction for agents to ship just-in-time…
Guillermo Rauch@rauchg
Vercel now has all the pieces in place to host at-scale backends. WebSockets, Queues, Workflows, Cron, Services, Containers, Python, Daemons, Long-duration Functions, Blob, Drives, Sandbox… Any guesses what comes next? [Quoting @vercel_dev]: WebSocket support…
Guillermo Rauch@rauchg
Vercel has proactively rolled out Firewall-level mitigations for today's Node.js RCE vulnerability, in advance of the official patch release. All traffic for all deployments is automatically protected. We're actively monitoring and rolling out managed runtime…
Guillermo Rauch@rauchg
DeepSeek v4.1 Flash (1017) is now included in ▲ Token Pass. Fast, mind-bogglingly cheap, and served with ZDR (zero-data retention). It's a phenomenal model to run subagents that execute plans conceived by larger and more expensive models. You can port TypeScr…
Guillermo Rauch@rauchg
It was inspiring to watch the behind-the-scenes¹ of the industry coming together, weeks in advance, to protect the world's infrastructure and mitigate php2shell. We deployed Vercel WAF mitigations that have already successfully prevented attempts on PHP origi…
Guillermo Rauch@rauchg
If you work on education, homeschool your kids, want to learn something new… check this out. You can use AI to create the coolest and most engaging explainers in the world. Grab a coding agent, ask it for an explainer, deploy it, share the link. So many ideas…
Guillermo Rauch@rauchg
Pi is one of the coolest projects in the AI world today. I'm on their team. Giving developers and companies choice of model, control over the runtime, data, skills, plugins… Excited to have great support on @vercel: [Quoting @pidotdev]: We have huge respect f…
Guillermo Rauch@rauchg
Much like we did with @aisdk, we're bringing a truly open-source, runtime-agnostic solution to harness durability. We're extending the durability infra that powers @eve and Workflows to all harnesses, like Pi and OpenCode. Local, Vercel, or DIY. Fun fact: eve…