Shopping is the most underrated agent use case. Everyone demos coding, but the pain most people actually have every week is 12 tabs of the same fucking air fryer and "where's my package?" lol. Grok Bot does that part now: > finds the best deal > compares items side by side > tracks all your orders in one place Give it a spin and lmk what you want next.

NEW: @bot tagging just went live. Reply to any post: > @bot add this to my Notion reading list > @bot remind me to read this tomorrow > @bot summarize this thread > @bot draft a reply to this Works in replies, posts, quote and lands right in your Grok Bot. What’s the first thing you’re handing it?

6 months ago I wrote that becoming a dad completely recalibrated what matters to me. Turns out I had no idea yet. She crawls now and sits on her own. Her first tooth is coming out since two days ago. She eats real food and smiles when she sees us but of course also cries when we leave the room. I’ve literally changed thousands of diapers. Slept less than I thought was humanly possible. Googled an unbelievable amount of stupid shit. And somehow every week it gets better (how the fuck?). The tiny newborn who used to just sleep on my chest is slowly turning into an actual little person with opinions, favorite foods, things she finds funny, and a very strong desire to put absolutely everything in her mouth. I still love work and probably still too obsessed with it. But six months later, the thing I wrote back then feels even more true: NOTHING comes close. Being her dad is literally the best thing that has ever happened to me.

Grok 4.7 is insanely good. The model is not the bottleneck anymore. I believe harness reliability and everything around it is... I read almost every comment on my "Week 1 at SpaceXAI" post, and one thing surprised me. Not many people said "make Grok smarter", but rather make the agents and bots finish the work 😅 > don't stop halfway through > don't lose the browser > don't forget what you're doing > don't get stuck and wait for me to notice That's actually a great problem to have. People are already using Grok for real work (love that!). Now the rest of the system needs to be as reliable as the model is capable. Tools, browser, memory, state, retries, errors... There are so many ways an agent can fail even when the model knows exactly what to do. Been working on some of that 👀

Week 1 at SpaceXAI. The intensity is real and the people are great, but there is so much information coming from every direction that you mostly absorb what you can and keep moving. Managed to fix a bug in Grok Bot browser use tho 😛 But a lot more exciting stuff coming. Grok is going to be great, and agents still have a long way to go. If you use or Grok Bot, what is the most urgent thing to fix right now (or what feature is really missing)?

SMTP is the new prompt injection 🚨👀 Giving an agent email gives anyone a way to put instructions in its context. That gets scary fast if your agent can also use files, send messages, access internal tools, etc. A malicious email doesn’t really need to “hack” the system. It just needs to convince the agent to do something it already has permission to do. The important takeaway from @adisingh: you can’t solve this inside the LLM You need: > permissions > sender/recipient restrictions > tenant isolation > action limits need to be enforced outside the model An agent inbox is basically an entry point into everything that agent can touch. Stay safe.

Introducing: Browser Use Box (bux). Your 24/7 personal agent box, powered by Browser Harness. ♞ We got tired of agents that vanish when you close the laptop. So we put them on a server. > 24/7 box that runs while you sleep > Real Chrome with persistent logins > Telegram baked in, text from anywhere I gave mine my email and a Telegram chat. It books flights, replies to LinkedIn and does my to-do list before I'm awake. Try it at ↓