You cannot build useful autonomous robots by relying on APIs and MCPs—you must give AI the ability to see a screen and use a mouse and keyboard like a human, because most services lack APIs.
Adcock explains that Hark's breakthrough is enabling AI to use computers like a human—moving cursors, typing, reading screens—because only one in a thousand websites have APIs, making API-based approaches fundamentally limited. ✦ AI generated
Brett Adcock · My First Million · 2026-08-14 · original ↗
starts at this moment · 4:04
“What did you guys do differently than the other because everyone's trying to do computer use, right?”
Fundamental to that thesis was like you got to figure out how to get AI to use computers general purpose. You would never hire an assistant that couldn't use a computer. So you got to be able to like give things out to it that can like do everything you can do. financial models, book flights, like order Door Dash, whatever you need to do, you need to be able to do it all autonomously, but only one in a thousand websites have APIs... That's what you have to do to solve like general purposeness for around a computer is you can't rely on API or MCP. You have to figure out how to like navigate like a human can.
verbatim transcript · starts at 4:04
3:48be like a human is going to have this like AI pairing. It's going to have like ultimately maybe your own AI weights, your own memories, maybe your own hardware. It's going like really close. And fundamental to that thesis was like you got to figure out how to get AI to use computers general purpose. You would never hire an assistant that couldn't use a computer. So you got to be able to
4:04like give things out to it that can like do everything you can do. financial models, book flights, like order Door Dash, whatever you need to do, you need to be able to do it all autonomously, but only one in a thousand websites have APIs. So, in most, you know, glo like most computer use globally is on the on the internet and browser. My my main inclination within two or three years,
4:23you'd have a system that you'd be able to talk to and say, "Go do this or do that." And to be able to like go off go online and like maybe maybe like use the internet really well like almost like a robot would where you can like move the mouse and use the keyboard. That's what you have to do to solve like general purposeness for around a computer is you
4:38you can't rely on API or MCP. You have to figure out how to like navigate like a human can. Now at Hark, we've like we just released our first uh kind of model and research preview um last week. It's really hard for us to find now something that we tell it to go do on the internet. It can't do. >> What did you guys do differently than
4:57the other because everyone's trying to do computer use, right? So like I think Elon's got macro hard and chatd had their computer use thing. Everybody's doing it. You guys feel like you've cracked something. What did you guys do differently? >> Okay, there's a couple things we did a little differently. First is like everybody's tackling this from like using APIs and MCPs. Like the reason Open Claw got so great, it was like it
5:15could only it couldn't use the brows. It couldn't like go on and use Door Dash end to end because Door Dash has no consumer API. So we tried to figure out how to use like a how to look at a screen and one is we spin up a virtual computer for every agent. So they don't need like a MacBook or anything. So you can just spin up as many of these