Full story
ChatGPT enters iMessage
OpenAI has launched an Apple Messages plug-in for ChatGPT that lets users connect their Messages inbox to the chatbot, with ChatGPT able to sort, analyze, edit, search, draft, delete, and even send messages on a user’s behalf.
“OpenAI told Bloomberg that the plug-in runs locally on a user’s machine”
The feature is positioned as an operator for the inbox itself, with a promotional video showing a user asking ChatGPT to suggest follow-up messages based on texts received the previous day.
OpenAI told Bloomberg that the plug-in runs locally on a user’s machine and “doesn’t create an index of all someone’s messages.”
OpenAI also warns users against enabling persistent approval, because it “removes your final chance to review a message before ChatGPT sends it as you.”
Consent-gated sending
OpenAI shipped the Apple Messages plugin for the ChatGPT desktop app on macOS, and it landed August 20, 2026, in the company’s release notes.
The plugin reads and searches a Mac’s iMessage, SMS, and RCS conversations and prepares or sends texts through the Messages app itself, but it ships only in the Apple Silicon (arm64) build of the desktop app.
By default, ChatGPT sends a message only after the user approves the content and the recipients, using an “Allow once” choice per send.
OpenAI’s plugin documentation discourages persistent approval, stating: “Keep per-send approval for chats that may contain untrusted or misleading instructions.”
Privacy and control stakes
The Messages integration is described as requiring careful oversight because it can access private conversations and other sensitive information stored in Apple’s Messages app, and it is framed as more sensitive than connecting something like Google Drive.
“OpenAI told Bloomberg that the plugin processes data locally on the user’s device”
OpenAI says the plugin processes data locally and does not create a general index of all their messages, but the company has not yet disclosed the technical details of how the mechanism works.
OpenAI advises users not to opt out of continuously confirming ChatGPT’s actions when sending texts, keeping the review step as the final opportunity to read a message before the chatbot sends it to another person.
TechCrunch reports that OpenAI encourages users to keep an eye on what ChatGPT is doing and discourages turning on persistent approval, warning that doing so “removes your final chance to review a message before ChatGPT sends it as you,” the company writes.
