- Openai brings agent mode to its Mac app
- Agent mode is available in the Toolbar menu
- Now you can leave long tasks running in the background while working on something else
Openai has added its new agent mode to its Chatgpt MacOS app and it is available right now if you are a plus subscriber. When using Chatgpt via the Mac app, you will see Agent as one of the settings on the toolbar that lives below the speed window. Choose it and now you are in agent mode.
Openai launched agent mode, or chatgpt agent, as it is also called last week, and it is a way of combining all the power in deep research with the agent’s characteristics of his former agent, called operator.
During the launch event, Sam Altman and CO showed several applications to agent, such as planning big events, such as a wedding or producing a presentation based on a wide range of data it should go off and find.
Openai describes Chatgpt -Agent as “Chatgpt, who can think and act, proactively choose from a toolbox with agent skills to perform tasks for you using his own computer.”
Look at
Alternative access
Openai also makes a version of its app for Windows users, but this has not added agent mode yet.
We have noticed that some people do not see the new agent icon on their toolbar on the Mac app yet.
Presumably this will be resolved when the change rolls out, but if you are using the Mac app and you do not see an agent button at the bottom of your interface, do not worry, you can still access agent mode.
Simply write a / and a list of settings appear, one of which is ‘Agent Mode’.
The Desktop app version of Chatgpt is more integrated into the operating system than simply using chatgpt in a web browser.
For example, you can start chatgpt from any screen on your desk with a keyboard shortcut. Use setting + space on macOS or Alt + space on Windows.
The Desktop version of the Chatgpt app also contains advanced voice mode, so you can chat with chat in real time using the microphone.
While we welcome the new chatgpt mode, it opens your Mac for more vulnerabilities. This was something that the Openai team treated at the launch, and Sam Altman said there could be a new wave of threats targeting AI agents who are simply trying to be helpful.
