Skip to main content

The ChatGPT app for Mac just got this helpful new feature

The OpenAI desktop app showing the text input window
OpenAI

OpenAI’s recently released Mac desktop app is getting a bit easier to use. The company has announced that the program will now offer side-by-side access to the ChatGPT text prompt when you press Option + Space.

The desktop version offers nearly identical functionality to the web-based iteration. Users can chat directly with the AI, query the system using natural language prompts in either text or voice, search through previous conversations, and upload documents and images for analysis. You can even take screenshots of either the entire screen or just a single window, for upload.

Recommended Videos

In one example provided by the company, a user snaps a screenshot of some computer code they’re working on and has ChatGPT analyze it, then provide suggestions on how to improve it.

Now, while the app runs locally, the machine learning still happens in OpenAI’s cloud, so you will need an internet connection to use it. You’ll also need to be running macOS 14 and Apple Silicon M1 or better (a Windows iteration is expected later this year.)

As you can see in the announcement video above, the desktop version even holds a few advantages over the online one. Users don’t actually have to upload entire documents for analysis, for example. You can simply highlight a selection of the document, then ask ChatGPT about it directly through the local text window.

And while it doesn’t (yet) offer Advanced Voice Mode, the desktop version does allow users to use the existing Standard Voice Mode, which still brings us tantalizingly close to a future where we can regularly start conversations by shouting “Computer!

Andrew Tarantola
Andrew Tarantola is a journalist with more than a decade reporting on emerging technologies ranging from robotics and machine…
Nvidia just released an open-source LLM to rival GPT-4
Nvidia CEO Jensen in front of a background.

Nvidia, which builds some of the most highly sought-after GPUs in the AI industry, has announced that it has released an open-source large language model that reportedly performs on par with leading proprietary models from OpenAI, Anthropic, Meta, and Google.

The company introduced its new NVLM 1.0 family in a recently released white paper, and it's spearheaded by the 72 billion-parameter NVLM-D-72B model. “We introduce NVLM 1.0, a family of frontier-class multimodal large language models that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models,” the researchers wrote.

Read more
ChatGPT’s Advanced Voice feature is finally rolling out to Plus and Teams subscribers
The Advanced Voice Mode's UI

OpenAI announced via Twitter on Tuesday that it will begin rolling out its Advanced Voice feature, as well as five new voices for the conversational AI, to subscribers of the Plus and Teams tiers throughout this week. Enterprise and Edu subscribers will gain access starting next week.

https://x.com/OpenAI/status/1838642444365369814

Read more
A modder just put ChatGPT on a TI-84 graphing calculator
A TI-84 calculator displayed next to a calculus textbook

Popular tech YouTuber ChromaLock recently shared a video demonstrating how they managed to connect a "dated" TI-84 graphing calculator to the internet and run ChatGPT, creating, "the ultimate cheating device."

In order to pull off the hack, ChromaLock leveraged custom hardware modifications and an open-source software suite. On the hardware side, the YouTuber installed a Wi-Fi-enabled microcontroller (specifically, the Seed Studio ESP32-C3), thereby avoiding the need to use the link port to connect to an external connectivity device. They had to tweak the device's voltage slightly and install a 1K resistor to properly power the microcontroller.

Read more