I’ve got a problem. I’m addicted to Grok Bot. I keep finding excuses to make another @grok @bot. Apparently I’ve made 81 bots since August. So the team gave me 50 codes to give away for a free month of Super ($100 tier). Haven’t tried it yet? Reply with what you’d build. I’ll pick 50 of the most interesting ideas. New users only.

In June, @SamAsante and I launched Typeahead, the first product from our new company. Today we're releasing our next Mac app. It's called Beam, and we're live on Product Hunt. I've got Macs all over my house doing different work. Some run agents and local models. Others handle builds. When I want to use one app on another Mac, I usually end up navigating a whole second desktop through Screen Sharing. Beam brings that app's window onto the Mac I'm using. It gets its own Dock icon and shows up in ⌘Tab. I can type into it and resize it while everything keeps running on the other Mac. Sam has put a lot of care into making this feel natural. The video shows it better than I can explain it. Live on Product Hunt →

Before I give any AI tool access, I want four answers. Can it draft instead of send? Can I start read-only? Can I see what it did? Does disconnect actually cut access? Tomorrow at 10 AM PT I’m walking through the permission settings in Muse, ChatGPT, Claude and Grok Bot, plus the failures that made the limits obvious.

Replit changed its product after Agent deleted database data during development. Development and production databases are separated now. During development, Agent cannot change production data. I like this kind of permission because the model does not need to remember a rule. Production sits outside the environment Agent can change. Friday at 10 AM PT I'm doing AI Permissions 101. I'll show more examples where the product itself decides how far the agent can go.

Two Grok Bots can look separate and still share the same computer. xAI says every Bot on your account uses the same persistent cloud computer. That includes files, browser sessions and command-line credentials. They explicitly tell you not to use separate Bots as a security boundary. Splitting work across Bots does not split the boundary underneath them. That is exactly the kind of thing I want to know before I connect an agent to anything important. Friday at 10 AM PT I'm doing AI Permissions 101. I'll show the settings and product details I look for before I hand an agent more work.

I’ve seen a couple of posts about this so wanted to demystify. Today, every Muse user gets a free computer in the cloud. It's a real computer, and we’ve designed the security architecture of the Muse Secure VM carefully so you and your Muse can do almost anything you could with a computer sitting under your desk while keeping you and the system safe from threats like prompt injection. We wrote about this at length in our security blog post – Activity in the “runtime cell”, which you share with your Muse is unfettered, but sensitive actions are all overseen by the Sentinel, which runs outside of that cell. Similarly, all sensitive secrets - like the passwords you enter into Muse’s secure credential storage - are also stored outside the runtime cell. The runtime cell gets its own root filesystem (including a full Ubuntu linux image) separate from the host filesystem where your other more sensitive data lives. Because it is isolated from the sensitive stuff that runs on the same box, this means that we can, and do, offer users full visibility and control over the files in the runtime cell. Just as you can when you install Linux on your home computer, you can poke around and see all the files that make the system work - both debian system files and the binaries and data files that implement the parts of Muse which run in the runtime cell. This was a very deliberate choice - your Muse Secure VM truly is your own computer in the cloud. You can install software in it, write and compile code, use the browser to surf the web: it is your own Linux box that you can operate as you choose with your Muse. Poking around in this computer doesn't give you any privileged access to Meta infrastructure, or to other people's data If I may geek out a little here for a second… As a kid I loved to take things apart to see how they worked. As a teenager I got into computers and soon found myself drawn to C:\WINDOWS\SYSTEM and the system registry, later Slackware’s /dev/, /proc/ etc – I could see how the system was laid out and as I explored what DLL files and .so files actually did, I gradually became able to meld the computer to my own will. We’re really proud to be able to put a real computer in millions of people’s hands with a similar level of transparency. We built a file explorer right into the Library tab of the UI. We want you to be able to see the markdown files Muse writes while it thinks about how to serve you better, and explore the internals of the system if you’d like to. So, when you ask your Muse to show you its entire filesystem, and receive gigabytes of files you’re seeing the full contents of the runtime cell. It’s yours to explore and enjoy! If you’re not a geek like me, or simply want to download the data that you personally have created directly with your Muse, we added a feature for that too in Settings > Data controls > Download your agent data.

There's nothing kind about letting good people live in a fantasy world that no longer exists. You have to tell them, even if it hurts. Because the sooner they accept reality, the sooner they can adapt to the future.

It's pencils down, people. Writing code by hand is no longer an economically viable skill for most programmers at most companies. But the future of making software has never been brighter. Don't you dare black pill this beautiful moment!

Muse can now shop for you. At Meta Connect yesterday, Meta said it can shop across Shopify and pay with Shop Pay or PayPal. It is also adding connectors for Walmart, Best Buy, Sephora, Wayfair and others. Once money moves, the permissions get a lot more specific. At checkout, Muse is supposed to stop and show you the exact purchase before anything is bought. If it uses the built-in wallet, Meta says the payment can be a single-use card limited to one merchant and one amount for a short window. Muse never gets your underlying card number. Meta also said Muse can operate apps on your Mac and keep working after you walk away. Soon it gets its own email address and comes to smart glasses, where it can help with what you're looking at. Amazon already blocked Muse from shopping on its site. So my approval is not enough. The merchant still gets a say. I want to know all of that before I let an agent spend money and keep working across my devices. Friday at 10 AM PT I'm doing AI Permissions 101. I'm bringing the actual permission screens from Muse, Grok Bot, Claude and others. The failures are coming too.

MUSE FEATURE ALERT: y'all have been asking for this one. your @muse is getting its own email address. add it to a thread or forward it stuff and it’ll handle it for you. muse mail!

Years ago, Gagan (@gaganbiyani) tried to hire me as an intern. It was a full-circle moment to interview him about Horowitz Andreessen Academy (@theacademysf). Some backstory: I studied Chemical Engineering at the University of Waterloo. Waterloo is famous for its co-op program - you can't get a Bachelor's until you complete 5 internships. Two co-ops in, I knew ChemEng wasn't my path. So I taught myself to code and set my sights on working in Silicon Valley. A surprising number of companies were willing to interview someone with no CS degree. One of them was Sprig, with Gagan as its founder. Once I got an offer, he got on the phone with me multiple times. He was trying to convince me to join, but what he actually did was convince me I belonged in tech. I ended up picking a more established company (might have been my loss). But I never forgot how confident and capable he made me feel. That's what @theacademysf is about: learning by building, and betting on capable students before they have the credentials. Gagan spent his entire career challenging the education system. I’m so excited for him to make this bet a reality! Interview dropping soon!

Been working on a real estate deal for a while. Yesterday I was told something was going to take 3-5 days to turn around. I asked why? Answer: Because that's how long it usually takes. Then I asked: What would happen if you called them and told them you need it tomorrow? My attorney said she'd try. So she did. And what do you know? They said they could turn it around in a day. Yet another reminder that the first answer is just a placeholder for "usually". If you settle for that, that's what you'll get. But there's another option on offer: The option you want. And if you don't ask, you don't get. And if you don't do, it won't be done. Everything can be compressed.

This is a treasure trove of hard-earned lessons. 1/ Shortly after I joined Stripe in 2019, we all went to Convergence (Stripe's employee conference). My manager pulled me aside and said: "You have to talk to Shreyas. You'll learn a ton". He was so right. I was lucky to learn from Shreyas during our time together at Stripe. 2/ Shreyas's video on talking to executives is spot on. At Cloudflare I had the opportunity to present to the entire C-suite every month on a critical initiative. I had to learn how to communicate with executives through my own mistakes. "CxO doesn't want to hear why X is impossible because of how card networks work. Work with Stripe, Treasury, and Finance to figure it out". → "Communicate at their level, not your level". I wish I'd seen Shreyas’s video back then!