**Claire Vo** (0:00)
What is stacked around your office right now?
**Alex Finn** (0:03)
I have three Mac Studio 512 gigabytes. We got a DGX Spark, as well as a computer. I just built an Rtx 5090 Basically at all times of the day, each one of these computers is just burning tokens. The number one pushback I get on all this is, your computers are so expensive. Isn't Cloud Models cheap? Isn't it $20 for a Chad GBT subscription? Well, that's not the point. The point is in pure ROI. The point is the use cases it unlocks. You now have, because you have AI models running locally, the ability to run unlimited intelligence around the clock 24-7. If you were to do that with a Cloud Model like Chad GBT or Claude, you would be spending outrageous amounts of money.
**Claire Vo** (0:49)
What else fun are you doing with AI?
**Alex Finn** (0:50)
The most fun I've been having lately is building out my software factory. I have two loops in Claude Code going. I have a build loop and a review loop. First, it has a build loop where it will take all those tasks and start building out the tasks it came with over and over and over again. Then it has a review loop that takes all the tasks that were built and has another agent go in and review it. Once that's reviewed, it pings me on Slack, and I can just leave a rocket emoji. When I leave the rocket emoji, it says merged, and my Henry loop goes in and merges it. It's been a blast cracking this nut of how do you build your own software factory.
**Claire Vo** (1:35)
Welcome back to How I AI. I'm Claire Vo, Product Leader and AI Obsessive, here on a mission to help you build better with these new tools. Today, I have Alex Finn, and he's going to walk us through his two Mac Studios, DGX Spark, and the Nvidia backed computer he built for himself, and demystify what it means to run local models and have ambient AI working for you 24 hours a day. Let's get to it. This episode is brought to you by Runway, a new kind of creative platform that has everything you need to generate any image, video, or piece of content you want, all in one place. With Runway, it's now possible to go from initial idea to a finished deliverable in a matter of minutes. From turning low fidelity product shots into campaign-ready imagery all the way through putting together big brand films, Runway can help your team scale your creative ambitions while keeping your budgets and timelines from doing the same.
Runway brings together the world's most advanced AI models, which is why enterprises like Microsoft, Robinhood, Amazon, and Adobe, along with studios like Lionsgate and Legendary, all use Runway to ship real work every day. Try it yourself at runwayml.com/howiai, promo code howiai.
Alex, welcome to How I AI Hardware Edition, Local Model Edition. I am so excited. Before we jump in, tell us just what is stacked around your office right now.
**Alex Finn** (3:13)
It feels like a sauna in this office right now, to be quite honest with you, because I got a lot going. I have three Mac Studio 512 gigabytes, which apparently puts me in the wealth class of Elon Musk having these now. I think they resell for like $30,000 each.
We got a DGX Spark, as well as a computer I just built two days ago, basically a big computer built around an Rtx 5090 So we have, I think, what's that come out, to five or six different computers for AI. So a lot of hardware around here.
**Claire Vo** (3:49)
And you are making really good use of it.
**Alex Finn** (3:51)
Yeah, so I use it basically as what I call ambient AI to support my entire life. And we'll go through all the things it's doing. But basically at all times of the day, each one of these computers is just burning tokens, doing things, helping my life, right? Unlimited AI is basically how local AI works. And I all have them doing jobs around the clock for me, which you really can't do with cloud APIs.
**Claire Vo** (4:16)
So how do we get here? How did you become hardware local model guy? Like, why is it so hot in your office?
What brought you to this moment?
**Alex Finn** (4:28)
My big awakening was back in January when I discovered OpenClaw. And so I was scrolling X one day on a Friday. I saw a blog post around OpenClaw. I opened it, I'm like, wow, this is really interesting. I'm like, don't know why, my gut instinct is like, I gotta go buy a Mac Mini. I go to this, this is before anyone was talking about OpenClaw, by the way.
29 more minutes of transcript below
Try it now — copy, paste, done:
curl -H "x-api-key: pt_demo" \
https://spoken.md/transcripts/1000651996090
Works with Claude, ChatGPT, Cursor, and any agent that makes HTTP calls.
From $0.10 per transcript. No subscription. Credits never expire.
Using your own key:
curl -H "x-api-key: YOUR_KEY" \
https://spoken.md/transcripts/1000776582970