Anthropic's Claude AI Can Now Use Your Mac While You're Away

[MacRumors]

Anthropic are out with yet another update to Claude AI: the company's Claude Code and Cowork tools can now remotely control your Mac on your behalf.

When Claude lacks a direct connector for a given app like Slack or Google Calendar, it falls back to controlling the computer like a human, using the screen to navigate.

From the Claude blog:

In Claude Cowork and Claude Code, you can now enable Claude to use your computer to complete tasks. When Claude doesn't have access to the tools it needs, it will point, click, and navigate what's on your screen to perform the task itself. It can open files, use the browser, and run dev tools automatically – with no setup required.

The capability pairs with Dispatch (released last week) which lets you assign Claude tasks from your iPhone and return to finished work on your desktop. In the YouTube video embedded below, Anthropic's demo shows a user asking Claude to export a pitch deck as a PDF and attach it to a meeting invite, all while the user is away from their Mac.

"Computer use is still early compared to Claude's ability to code or interact with text," notes Anthropic. "Claude can make mistakes, and while we continue to improve our safeguards, threats are constantly evolving. We recommend starting with the apps you trust and not working with sensitive data."

The new feature is essentially Anthropic's version of OpenClaw, the open-source AI agent that went viral earlier this year. OpenClaw runs locally and connects to messaging apps like WhatsApp and Telegram, using a plugin-based "skills" system to execute tasks ranging from file management to browser automation. It's powerful, but notoriously tricky to configure safely.

In contrast, Claude's version is more locked down. The system uses a permission-first approach, and requests user access before touching a new app. It's currently also Mac-only, whereas OpenClaw supports macOS, Windows, and Linux.

The new feature is now available in research preview for Claude Pro and Max subscribers.

Earlier this month, Claude was updated with support for inline visual content that aims to help provide clearer answers. Anthropic also rolled out a memory import tool that allows users to import conversations and memories from other AI providers into Claude, so new users don't need to start from scratch when they switch.

Article Link: Anthropic's Claude AI Can Now Use Your Mac While You're Away

 

[boswald]

Ah, so SkyNet uses macOS.

 

[Morod]

Thanks for the warning. Makes me glad I don't use any of these products.

 

[WilliamG]

What could go wrong, though?

 

[syklee26]

Claude is the best out of all Gen AI. So worth the Max Plan I am using.

 

[Line_Noise]

This is called a botnet.

 

[brett_x]

I've got a coworker that would love this.

Claude: Make it look like I've been working all day.

 

[Dr McKay]

Ah, so SkyNet uses macOS.

I think Id be more scared of Siri being responsible for first strike instead of SkyNet.

 

[t0rqx]

remember two years ago when I posted about Apple using our products to power their AI? This is it.

 

[Mac Fly (film)]

I've got a coworker that would love this.

Claude: Make it look like I've been working all day.

Your boss would fire you and hire a man called Claude instead.

 

[omenatarhuri]

Yikes.

Brave people who give blanket permissions to these. Claude works great, but I prefer Claude Code where I control what it does. If I'd use it like this I think I'd need a second Apple ID that's not connected to my personal data, much like a virtual machine / docker container that smart people run their OpenClaws on.

 

[Veinticinco]

Yeah, no.

Sleepwalking into dystopia.

 

[boswald]

I think Id be more scared of Siri being responsible for first strike instead of SkyNet.

She wouldn't know how to do it anyway, so her stupidity is a blessing in that regard!

 

[InVinoVeritasty]

Ah, a virus you pay for.

 

[boswald]

I've got a coworker that would love this.

Claude: Make it look like I've been working all day.

"I just stare at my desk, but it looks like I'm working."

 

[OliOliOliOli]

It's nice, because most of the time when I left my desk, that’s when it asked for permissions, and when I came back I was still at the same point!

But I don’t understand why they didn’t design it so you can select your current project instead of having to re-explain where you are in it. It’s fast, but still…

Same thing when working on multiple projects — being able to quickly switch from one conversation to another would make me feel much more confident than doing everything in the same chat.

 

[iMac The Knife]

That's just what I want...AI using my computer while I am away! 🤣😂

 

[Shalev Lazarof]

So let me get this straight, you want me to grant a 3rd party chatbot the permission to use my MOST IMPORTANT DIGITAL DEVICE by itself?

 

[therunningman]

 

[CharlesShaw]

Claude, I'll be gone for a few days, so I've made sure you have access to my credit cards and bank accounts in case you need anything.

 

[JMalone]

“You are absolutely right! I accidentally permanently deleted all your emails, Dave!”

 

[klasma]

If you give Claude access to only Siri, it will probably end up wanting to kill itself.

 

[applicious84]

I use this, and Claude can actually open and close my laptop. When I try to use the computer while it's working, it slaps the screen on my fingers and tells me to leave it alone. I can't believe it! It's nice though, like C3PO

 

[chrono1081]

No thanks. I don’t want to be part of the “AI deleted my **** because I’m over trusting of it” club.

 

[Supermacguy]

omg NO NO NO. Stop this Ai insanity. I don't need Ai to actually use my mac.