zer0nerd

Every chat platform has its own event model, threading system, and streaming quirks. We felt this pain internally when we challenged every team to build agents to multiply their output, and the agents were easier than the chat plumbing. So we built Chat SDK to remove that bottleneck. Get started directly or via your coding agents with: ▲ ~/ 𝚗𝚙𝚖 𝚒 𝚌𝚑𝚊𝚝 ▲ ~/ 𝚗𝚙𝚡 𝚜𝚔𝚒𝚕𝚕𝚜 𝚊𝚍𝚍 𝚟𝚎𝚛𝚌𝚎𝚕/𝚌𝚑𝚊𝚝 Read more ↓ vercel.com/blog/chat-sdk-…

@vercel @cramforce This is good. Do we know if this is going to be fedramped?

Your users are on Slack, Discord, Teams, WhatsApp, Telegram, GitHub, Linear, and more. Your agents should be too. Chat SDK lets your agents run on every platform from a single codebase. Watch the announcement ↓

@elevenlabs … and I’m here one hour late 😭

We raised $500M at an $11B valuation to transform how people interact with technology.

@resend Me

We're giving away 50 hoodies today! 🎁 Stay cozy AND rep your favorite email API—what could be better? Just drop a comment, and we'll DM the first 50 who respond with instructions. You'll need a @resend account (free or pro) to get it. Happy holidays! 🎄

@rauchg @Reuters @clay @aisdk Thank you so much!

@rauchg @Reuters @clay @aisdk @rauchg is Fedramp in the pipelines for vercel?

AI SDK v6 • Agents • MCP • Tool Improvements • Tool Calling with Structured Output • DevTools • Reranking • Standard JSON Schema • Image Editing … and more 🤯 vercel.com/blog/ai-sdk-6

@rauchg @parzerp @vercel Can this be automated for the folks that have over 20+ apps on vercel? I don’t mind if your team just goes and makes the update.

@parzerp @vercel We’ll take a look. Thanks for the feedback

.@vercel @rauchg suggestion: replace or stack the Node 18 warning with the new red nextjs upgrade notice at the dashboard/org level, don't just show it on the project pages back when you guys announced the node 18 deprecation and started showing that banner on the overview page we had lots of non-client+nontech companies reach out for help now with react2shell almost nobody has, so far it seems to be only people who actively use vercel analytics and encounter the red banner this way

@rauchg Thank you G

If you’re on Vercel, the WAF is on automatically. No action needed other than upgrading your deps and re-deploying.

We’ve got confirmation of a working #react2shell POC being shared. We’ve verified Vercel’s Web Application Firewall is successfully blocking this known variant. We are also seeing bad actors attempt exploitation. Upgrading React & frameworks remains a top priority.

@anything Add @instant_db and I’ll use it

Build with Anything Max and aim for $10K MRR in the next 30 days. First person to - Hit $500 MRR - wins $20k - Get 50 paid users - wins $20k - Highest MRR after 30 days - wins $20k - Best designed app - wins $20k - Most viral app - wins $20k LFG!

Introducing Anything Max: Vibe Coding that's leaps above Lovable and Bolt We've raised money at a $100M valuation and built what we believe is the future of vibe coding. We asked 100 vibe coders to build their apps side by side on Lovable, Bolt, and Anything Max and they rated Anything Max the winner across all 3 categories - accuracy, design, and 'overall'. Here's why: • Full-stack control: Max can test backend hooks, branch database states, and debug issues, because Anything owns the full infrastructure. • Max can load up your app in its own browser and click on all buttons like a human tester to find all edge case bugs, then trace the bug across the stack - could be a frontend, backend, or a database issue (only we can do this, read #1) and autonomously fix it with 97% accuracy. Lovable and Bolt build prototypes, but Max users are building production-ready apps and already charging money for them. Blake built a gut biome app to $10K run rate Anthony built a referral tool to $20k in revenue Yuri built a suite of apps doing $40K Build your app with Max: createanything.com/max -------------------------------------------- We're hosting a $100K Hackathon to help people grow their app to $10K MRR. - We'll teach you everything we know about growing to 1M users. - You'll have 30 days to build a real product in public and get paying customers for it. If you do it well, you can start the New Year with a functioning business. Retweet and comment “LFG”, and we’ll send you a $100 discount code and the link to participate

@instant_db Could this be automated? Let’s say I want to create a time series and only retain data for a period of time, that way I stay within the 1GB. Or is that against an instant policy?

🔥Instant CLI just got an upgrade! You can now: 1. Delete columns and links 2. Rename columns and links And if anything goes wrong, you can undo!

@adamcohenhillel @rauchg How do we get this to be a class in school? Or an afterschool program for kids? There is so much potential but commmunity leaders are to afraid.

Enjoyed my discussion with Vercel CEO @rauchg on how AI education and literacy will keep our free societies ahead. We spoke about AI empowering everyone to build software and the importance of ensuring it serves quality and progress. Optimistic for growth, prosperity and greatness for Vercel and its supporters

@rauchg @nextjs @vercel I get this weird scroll behavior on iOS 18.6.2

We have now shipped two experiences, grep.app and vercel.domains, with pretty fast search over humongous datasets. They highlight what @nextjs and @vercel have to offer: client and cloud working together in the service of user experience.

@rajbreno Someone please help explain to me how you get less than 500 Claude Sonnet 4 requests when before they counted as .75 of one full request compared to Claude 3.5.

@kinder_grinder I hope someone with more exposure to cursor can help you and answer your question

thats what I am using and doing right now exactly. We buld a document with step by step implementation and its follow along one step at a time, so it does not go out of the context window when working on big feature or refactor. But I am wondering if there is a better model, like Gemini or even using Auto mode?

A genuine question: What model are you using in Cursor for agent mode? I switched to Cursor 5 days ago and I love it. I was a heavy v0 user, and their pricing made me switch. I'm glad, v0 seems like a toy compared to Cursor. Are you using Auto mode or a specific model?

@kinder_grinder @v0 Perhaps do something like cursor and add reasoning to detect bad responses so they don’t get charged. On a positive note v0 chat is the only one that doesn’t insult or replies with bad words or toxicity like your competition.. or even cursor.

.. @v0 now feels like a slot machine. Sometimes you win, sometimes you lose. Most of the time, you lose, and it costs you.

@kinder_grinder @v0 @evilrabbit_ runtime errors should not be charged. If the user reports a bad response then it should not be charged. If the Ai chat suddenly stops or hangs, and the user needs to restart the prompt; then the user should not be charged.

@instant_db How do you do increments or setup the schema or code to just do a +1. I find it very difficult to figure this out. I just want to have a metrics table with increments

We added `ruleParams` to permissions. You can use them to write rules like: “You can edit this document, if you have the link to it” And to show this off, we built the coolest reactive, offline, "Was this page helpful?” component: See for yourself: (sound on!)

@leerob Try cursor with the same prompt. I’m intrigued

I know there's a bunch of other agents (haven't tried them all) and also that some of these products are super early, so take this all with a grain on salt! Just wanted to share my experience here on an older codebase.

So I gave the same task to Codex, Jules, and Devin Let's see what these AI Agents are all about... Do they actually work?

@viberank @v0 I like your idea!