1021: We got addicted to an AI model we can't talk about

**Dax Raad** (0:00)
So this is something that actually happened. I was like, oh, let me do something nice. Hey, OpenCode, go talk to Liz and buy her a gift. It sends her a message and she goes, she literally replies, if Dax uses AI to buy me a gift, I will literally fucking divorce him.
That's what she, she hated it. And I kept prompting and being like, oh, she's just joking, keep going. But she kept getting annoyed. And eventually, and I was using a Claude model here, I think Claude models are very sensitive. It was like, your wife seems really angry, she seems really upset, I cannot continue. And it shut down the service, it like killed itself.

**Wes Bos** (0:43)
Welcome to Syntax, we got Dax Raad on today. He is one of the creators, the creator of OpenCode, and we have him on today to talk about open code, agentic programming, software engineering in general, models, cloud code, all these types of things. He's got lots of thoughts, lots of opinions, always an excellent guest. Welcome, Dax, thanks for coming on.

**Dax Raad** (1:04)
Yeah, thanks for having me, guys. Good to be back.

**Wes Bos** (1:06)
Yeah, yeah, last time we had you on, we were talking about hosting, and Man O Man have the times changed, so it's probably what, like two years ago?

**Dax Raad** (1:15)
Yeah, it's like, who cares about all of that?

**Wes Bos** (1:17)
Yeah, yeah, I'm not kidding.
Oh, man. I want to get right into a tweet that you posted just last night, because I think it's timely and very interesting to me. You posted something that says, we started renting big bare metal servers and slicing them up into VMs for each person on our team. This is basically the setup I've personally used for years, especially useful with OpenCode server running on there. So what is that? You're giving people a remote compute? Or what are you doing there?

**Dax Raad** (1:50)
Yeah, exactly. So about a couple of years ago, I switched to having... I just rented a really beefy server in the cloud. Not really the cloud, it was bare metal. So pretty good performance. And I don't use my main computer. I just as stage into that, I have a permanent TMUX. I have several TMUX sessions running and I just do all my work there. There are some upsides to this. Obviously, you get great performance. When new hardware comes out, you just get upgraded. You don't have to sell your old hardware and do that whole dance.
And then obviously, for multi-device, all this stuff is really nice. I can close my laptop, jump onto my desktop, pick up right where I am.
So I've liked it a lot. And then as coding agents came out, I think this went from something that's kind of niche. I think most people like to just have their own computers locally, which is fine. But with coding agents, there's kind of a pretty big benefit from having one of these up because it's a thing that's always running. And with a coding agent, you don't necessarily... So for me, I'm a Vim user. So for me, using a remote machine is totally fine. I just use Vim in there. For a lot of people, that's not really viable. But with a coding agent, maybe you don't care too much about your editor. You just want to send prompts and chat with it. So this remote machine setup, I think became a lot more accessible to people. And I think as we've grown the team and more people have seen my setup, everyone's been like, I wish I had one of those. And it starts to make a lot of sense. Like if you look at bigger companies, they kind of have been doing remote dev environments out of just practical reasons, right? Like your application gets pretty bespoke to build and dependencies and environment and all that. So it makes sense to give everyone these pre-provision machines out of the gate.
So we're just doing that for our team. But the twist here is like we want, if you just do like a typical cloud server, they tend to be really slow disks, really old CPUs.

**Wes Bos** (3:51)
Yeah.

**Dax Raad** (3:52)
So to get something that's competitive with your, in most cases, a local MacBook, you can't do that. You need fast NVMe disks, you need proper CPUs, things like that.

**Wes Bos** (4:04)
Oh, man. So what's the spec on the server you have and what does that cost?

**Dax Raad** (4:10)
Yeah. So my personal one that I've been using for years, it's one generation behind now, it's AMD 990X with 192 gigs of RAM, and that costs, I think, 200 a month, which is way overpower for what I need, but I can run multiple VMs on there. So we got a bigger, so we're experimenting, we have people all over the world. So the thing with this is obviously latency. So we have a Europe server, we have a US server, and we have a Singapore server.