As part of the ongoing story, one of the ways for ChatGPT to escape the chatbox is with plugins, and a just-dropped plugin that lets ChatGPT tap into Apple’s Messages app is — unsurprisingly — getting a lot of attention.
As part of the ongoing story, available now in the ChatGPT plugins directory (it’s in the Public section, or you can just search for it), the fresh tool lets the ChatGPT app for Mac search conversations in the Messages app, give you summaries of your current messages, and even draft replies and send them, either with or without your permission.
In a fresh development, the plugin doesn’t work on the mobile version of ChatGPT (or at least not yet), and it can’t be accessed remotely. For now, ChatGPT’s Apple Messages plugin only works on the ChatGPT app for Mac (sorry, Windows users), and it runs directly on your Mac.
According to the latest update, so if the idea of ChatGPT of reading and sending messages to your contacts is unnerving, just know it’s been happening for awhile. Now, this kind of “search for and send messages” ability is nothing fresh; ChatGPT has long had a similar plugin for Gmail that can search your inbox as well as send Gmail messages on your behalf.
As part of the ongoing story, i’ll get to that in a moment. Still, while testing ChatGPT’s Apple Messages plugin, I got an unsettling surprise involving a different and even more powerful ChatGPT capability.
The report highlights that if you’re balking at the idea of giving ChatGPT full disk access to your Mac, that’s a wise instinct. I went ahead and click Allow because, well, that’s what I’m here for, right? Installing ChatGPT’s Apple Messages plugin involves giving the ChatGPT app permission to send messages, access your contacts, and — gulp — full disk access to your system, which it needs in order to search conversations in the messages app.
According to the latest update, you’ll need to give ChatGPT some wide-ranging permissions before installing the Apple Messages pluging.
According to the latest update, “Tell me about my most recent conversations,” I prompted, and ChatGPT dutifully summarized six of my recent chat threads, including a few with family members as well as one from Verizon and another from Roto-Rooter (they came to fix a leaky drain earlier this week). Having granted those fairly extensive permissions to the Messages app (again, I’m not suggestion you do this yourself), I began some light testing.
In a fresh development, chatGPT thought for a moment, and then a model popped up at the bottom of the screen with a draft message and a “Send this to … “ prompt. I clicked Continue, and boom — the message was sent. I also tried testing the Messages plugin’s ability to send messages, asking ChatGPT to send my wife a “this is a test” message.
Industry observers note that there’s also an “Always allow sending to this chat” option that OpenAI recommends leaving off, unless you want ChatGPT firing off messages to your contacts before getting a chance to review them. By default, ChatGPT will run a draft by you before sending any message via the Messages plugin.
In a fresh development, i also asked the Messages plugin to search for spam messages that I could safely delete, and it quickly popped up a series of conversations, from political fundraising texts and investment pitches to random newsletters and marketing messages.
The report highlights that without giving it too much thought, I then asked ChatGPT to go ahead and delete those messages, and here’s where the “uh, what’s happening?” surprise began.
The report highlights that but since I’d asked ChatGPT for just that — to delete those spam messages — it went about looking for another way to do so. You see, the Messages plugin for ChatGPT can scan your messages and send them, but it can’t delete your messages.
According to the latest update, suddenly, I saw screenshots of the actual Messages app in the ChatGPT interface, and I watched as ChatGPT took control of the Messages window and began browsing through my conversation threads on its own.
In a fresh development, you can see a thumbnail on the right of ChatGPT controlling the actual Messages app on my Mac.
According to the latest update, when it found the spam conversations, it used my Mac’s mouse pointer to click the Delete button, thus fulfilling my request.
The report highlights that instead, it took advantage of the “computer use” abilities I’d granted it for a previous test — abilities that I’d forgotten to rescind once the test was over. Just to be clear, ChatGPT didn’t break out of its bounds or do anything unauthorized here.
As part of the ongoing story, so while I was surprised and unsettled when ChatGPT briefly took control of my Mac, it was only doing what I’d previously given it permission to do.
As part of the ongoing story, minor though it was, the episode serves as a grim reminder of one of the greatest dangers of AI: the unintended consequences of seemingly benign AI requests.
As part of the ongoing story, the consequences in this case were no big deal, but if I made this mistake and I’m (supposedly) an experienced and careful ChatGPT user, well … it makes you wonder.
As part of the ongoing story, his coverage of artificial intelligence interrogates the most recent LLMs, and how they can be used at work and at home to be best prepared for the AI revolution. “AI is going to change our lives sooner than we think,” Ben writes. “Our best way to adapt is by using it every day.” Ben has been a PCWorld author since 2014, and has covered everything from laptops to security cameras before launching PCWorld’s AI beat. Ben's articles have also appeared in PC Magazine, TIME, Wired, CNET, Men's Fitness, Mobile Magazine, and more. Ben holds a master's degree in English literature. Ben has been writing about consumer technology for more than 20 years, and now focuses his reporting on AI as it relates to the basic human experience.