OpenAI Enhances ChatGPT Desktop Apps with Advanced Integration Features

ChatGPT for desktop, DeepL's voice translator, and startups get millions: This week's AI launches

OpenAI made its ChatGPT desktop app for Windows available to all users this week, including those using the app for free. Windows 10 and 11 users can ask the ChatGPT app questions, use it to search the web, share screenshots, and upload multiple files and photos. ChatGPT's Advanced Voice feature is also accessible for users to talk in real-time with the AI chatbot. The ChatGPT desktop app for macOS, in early beta, is starting to work with developer tools such as VS Code, Xcode, Terminal, and iTerm 2, the startup said. OpenAI plans to add more desktop apps. The update is available to ChatGPT Plus and Team users, and will roll out to Enterprise and Edu users in the future. Instead of pasting code into the AI chatbot, users can manually connect their IDE or terminal to the app, allowing it to look at the content and provide faster answers with more context, OpenAI said.

ChatGPT updates for Windows and macOS: Everything you need to know

OpenAI announced the news on Thursday, sharing how ChatGPT Windows app has Advanced Voice mode, as well as its latest model o1-preview. Windows users can use the Alt + Space shortcut to invoke ChatGPT. Users can also search the web, share screenshots and upload files and photos to the app. The desktop app is available to Windows 10 and 11 versions. The ChatGPT desktop app for Macs has been out since last May, but it got some updates, too. OpenAI has added integration with developer tools like VS Code, Xcode, Terminal, and iTerm2, so users don't have to manually copy and past code into the chat. Integration with coding tools is available for ChatGPT Plus and Team users, with Enterprise and Edu access coming in the next few weeks. An OpenAI spokesperson said they plan to add access to more apps soon. Desktop apps with third-party app integration and contextual understanding positions ChatGPT as a more useful tool to compete with Microsoft Copilot and Google Gemini. To further complicate things, OpenAI's AI models underpin Copilot and OpenAI also has a partnership with Apple to bring ChatGPT integration to Macs. Copilot and Gemini still have an edge over the standalone ChatGPT app because they're deeply integrated into Microsoft and Google's respective ecosystems, seamlessly connecting to software that users are already familiar with. Copilot works with Windows 10 and 11, Microsoft 365 apps, and Edge. Gemini has various levels of integration with Gmail, Docs, Chrome, and more; the Google AI tool is also housed inside the latest Chromebooks. As the race for AI dominance barrels ahead, the next phase is shaping up to be all about agents that can perform tasks on the user's behalf. Microsoft already has customizable agents with Copilot Studio, and both Google and OpenAI are rumored to be launching their own AI agents for browsing the web and other tasks. Advancement of desktop apps creates deeper integration into users' daily lives, which might become more useful with agents capable of multi-step reasoning.

OpenAI just made macOS smarter with ChatGPT app support

OpenAI has launched a major update for its ChatGPT app on macOS, introducing integration capabilities with various third-party applications, significantly enhancing the productivity of Mac users. Users can now interact seamlessly with developer tools like Xcode, VS Code, Terminal, and iTerm2, simplifying the process of coding and debugging. The newfound ability allows ChatGPT to read content directly from multiple applications without the need for manual copying and pasting. This integration facilitates a more intuitive workflow for developers. In a demonstration, ChatGPT effectively understood code from an Xcode project and offered accurate suggestions, thereby acting as an interactive coding assistant. Developers can now send a selection of code from apps like Xcode directly to ChatGPT, streamlining tasks such as adding missing elements to a project. For instance, when an OpenAI employee prompted ChatGPT to "add the missing planets" to a simple solar system model in Xcode, it efficiently generated code to represent Earth within the existing framework. Importantly, the new integration leverages macOS's Accessibility API, allowing ChatGPT to read text but not interpret images or videos. This limitation ensures the tool remains focused on text-based queries and code reading, optimizing its assistance without overstepping privacy boundaries. Currently, the integration with third-party apps is available to ChatGPT Plus and Team subscribers, with plans for expanding access to Enterprise and Educational users in the coming weeks. While OpenAI aims to make the feature widely accessible, the timeline remains uncertain. Users maintain control over which applications ChatGPT can access, ensuring privacy is respected with the option to revoke permissions at any time. OpenAI's continual expansion of functionalities mirrors Apple's own developments. With the upcoming macOS 15.2 -- currently in beta -- Siri will gain similar ChatGPT capabilities, like answering questions based on on-screen content. However, this integration is limited to interactions without specific app compatibility for now. In addition to enhancing ChatGPT's capabilities for macOS users, OpenAI is also releasing its ChatGPT Windows app for free users. This move signifies broader accessibility and a growing commitment to integrating AI across platforms, making advanced AI tools more available to users in various work environments. This latest update not only marks a significant step in the evolution of ChatGPT as a coding aid but also highlights the ongoing collaboration between OpenAI and larger software ecosystems to empower users. Whether you're diving into programming or managing a multi-app workflow, ChatGPT's new features are crafted to save developers valuable time and create a more cohesive working environment.

ChatGPT will soon be able to see your Mac apps and provide real-time advice -- this is huge

ChatGPT is now able to access the contents of your apps on macOS. The new feature is designed to make it easier to get the AI's input on what you're doing in another app without having to take a screenshot or copy and paste text. OpenAI announced the ChatGPT Desktop app for macOS in May and has been gradually improving it ever since, including most recently bringing Advanced Voice to the desktop for the first time. The new feature will initially only work with developer apps such as Apple's own developer environment Xcode and the Microsoft-backed Visual Studio Code. It will also have access to the Terminal, so all users could soon become power users. App insight features will only be available for ChatGPT Desktop on the Mac. Anyone with a paid account will be able to get access although it will take a few weeks to come to enterprise and education users. A spokesperson for OpenAI told Tom's Guide that while at the moment ChatGPT can only see what you're doing in the app and make suggestions, the company is exploring ways to make applying those suggestions more seamless. OpenAI stressed this was an 'early beta' and the focus was on making it easier for developers to work on projects with ChatGPT. However, the company says there are plans to add more apps soon -- so it could integrate with Word or even a game. A spokesperson explained that the main use case was to cut down on copy-pasting between ChatGPT and another app. For developers, they can connect the terminal or developer environment to ChatGPT and it can "then look at the content in that app to give you faster and more context-based answers to your questions." This brings ChatGPT closer to providing some of the same functionality developers, and newcomers to programming, are loving from Cursor and similar apps. In the future this could be expanded to allow ChatGPT to provide live information while you're in a Zoom meeting, or even give you tips on your gameplay in Civilization 7 -- which is coming to Mac on Day One of release. OpenAI says users will always know what ChatGPT is looking at, it won't be able to change anything in the app and it's a feature you'll have to explicitly enable. The capabilities and just how well it performs at working with apps will improve quickly. ChatGPT Desktop for Windows is now free for all users. Anyone with a free or paid account will be able to make use of the app in Windows 10 or 11. Previously it was restricted to people paying at least $20 a month for their AI fix. OpenAI says its windows desktop app lets you "seamlessly integrate ChatGPT into anything you're doing on your computer." This includes the Alt + Space shortcut that brings up a mini window and a companion window for quick access. Windows desktop now includes Advanced Voice, ChatGPT Search and the ability to share screenshots with ChatGPT -- something not available in the earlier release.

ChatGPT Can Now Access macOS Apps - VSCode, Terminal, Xcode and More

OpenAI has unveiled a new feature for the ChatGPT Desktop app on macOS, transforming coding workflows by seamlessly integrating with popular development tools. This integration marks a significant leap forward in the evolution of interactive coding assistants, offering Mac developers a powerful ally in their daily tasks. For those of us who have spent countless hours debugging code or managing dependencies, the idea of having an AI-powered ally sounds like a dream come true. OpenAI's latest feature for the ChatGPT desktop app on macOS is turning this dream into reality by integrating directly with popular development tools like VS Code, Xcode, Terminal, and more. Removing the need for you to cut and paste code from your favourite code editor into ChatGPT and vice versa. ChatGPT can now access the code directly from the application and answer your questions with full code context provided automatically. This new capability promises to transform the way developers interact with their code, making the development process more intuitive and efficient. Instead of juggling multiple windows and copying snippets of code back and forth, ChatGPT is right there with you, reading your code directly from your applications. It offers real-time suggestions, helps troubleshoot errors, and even assists with writing commit messages -- all without breaking your flow. While there are still some limitations, such as the inability to execute commands or write to files, the potential for future enhancements is exciting and you can expect new features to be continually added to the integration overtime. This integration is just the beginning of a more interactive and streamlined coding experience, setting the stage for a future where AI becomes an indispensable part of your development toolkit. The new ChatGPT desktop app now interfaces directly with: This integration allows ChatGPT to read code directly from these applications, eliminating the need for manual copy-pasting and streamlining the development process. By understanding the context of your code, ChatGPT can provide more accurate and relevant assistance, enhancing your productivity and code quality. With its ability to read and analyze code in real-time, ChatGPT offers developers a range of benefits: For instance, while working on a complex algorithm in VS Code, ChatGPT can offer real-time suggestions to optimize your code structure or improve its efficiency. This immediate feedback loop allows you to refine your code as you write, potentially catching issues before they become deeply embedded in your project. Explore further guides and articles from our vast library that you may find relevant to your interests in Application Context Access. Beyond code analysis, ChatGPT supports various ancillary development tasks: Version Control Assistance: ChatGPT can help craft meaningful commit messages by analyzing changes in your codebase. This ensures clarity and consistency in your version control practices, making it easier for team members to understand the evolution of the project. Dependency Management: When working in Terminal or iTerm2, ChatGPT can interpret command-line outputs and recommend actions for dependency installation or updates. This feature simplifies the often complex process of managing project dependencies, allowing you to focus more on core development tasks. Documentation Support: ChatGPT can assist in generating or improving code documentation, making sure that your projects remain well-documented and maintainable over time. While powerful, the current iteration of ChatGPT's desktop integration has some limitations: To enable this feature, users must download a specific extension for VS Code and adjust their security preferences to grant ChatGPT the necessary access. This setup ensures that your development environment remains secure while using AI assistance. OpenAI has ambitious plans to expand ChatGPT's capabilities in future updates: These potential enhancements aim to create an even more integrated and interactive development tool, further streamlining workflows and boosting productivity. The integration of ChatGPT with macOS development tools represents a significant advancement in coding workflows. By automating routine tasks, providing intelligent suggestions, and offering contextual assistance, ChatGPT enables developers to focus on higher-level problem-solving and creative coding. As this technology matures, it has the potential to reshape how developers approach their work, fostering more efficient, accurate, and innovative coding practices. While currently in beta, early user feedback highlights the value of accessing multiple application contexts simultaneously, pointing towards a future where AI-driven tools become an indispensable part of the development ecosystem. In conclusion, ChatGPT's desktop integration with key development tools marks a significant step towards more intelligent and responsive coding environments. As developers adapt to and use these new capabilities, we can expect to see improvements in code quality, development speed, and overall project outcomes.

ChatGPT can now read some of your Mac's desktop apps

OpenAI's ChatGPT is starting to work with other apps on your computer. On Thursday, the startup announced the ChatGPT desktop app for MacOS can now read code in a handful of developer-focused coding apps, such as VS Code, Xcode, TextEdit, Terminal, and iTerm2. That means developers will no longer have to copy and paste their code into ChatGPT, which has become a common way to use the chatbot. Now, when the feature is enabled, OpenAI will automatically send the section of code you're working on through its chatbot as context, alongside your prompt. However, unlike popular AI coding tools such as Cursor or GitHub Copilot, ChatGPT is currently unable to write code directly into developer apps on your behalf. The feature, called Work with Apps, is far from an AI agent, but OpenAI says getting ChatGPT to understand other apps is a "key building block" towards building agentic systems. One of the biggest challenges facing AI agents today is getting them to understand the rest of your computer screen, as opposed to prompts or their own responses. OpenAI says it's focusing this feature on coding apps to start; this is likely because AI coding assistants have taken off as one of the most popular use cases for LLMs. The feature is available to Plus and Teams users today, and will roll out to Enterprise and Edu in the next few weeks. OpenAI says ChatGPT will be able to work with other types of apps moving forward, specifically, text-based apps that could be used for writing tasks. In a demo with TechCrunch, an OpenAI employee opened the ChatGPT app and an Xcode environment containing a simple project modeling the solar system - although it was missing the Earth. The employee selected an Xcode tab within ChatGPT, which tells the AI chatbot to look at the app, and prompted the chatbot to "add the missing planets." The chatbot was able to complete the task, writing a line of code to represent the Earth that matched the rest of the project's format. They still had to paste ChatGPT's answer back into their environment, though. In order to read different apps, OpenAI is mostly relying on the MacOS Accessibility API to read text and translate it to ChatGPT, according to OpenAI desktop product lead Alexander Embiricos. MacOS's screen reader, which helps Apple's VoiceOver feature work, has been around for nearly two decades. It's generally considered pretty reliable for most common apps, but not everything. For some apps, such as Microsoft's VS Code, Work with Apps requires users to install a special extension to query content. And, as the name suggests, Apple's screen reader can only read text, so it can't help ChatGPT understand visual elements - such as photos, the orientation of objects, or videos. Work with Apps with send your last 200 lines of code through ChatGPT alongside every prompt for certain apps. For others, all the code in your foremost window will be used as input for the chatbot. You can highlight sections of code or text to help ChatGPT focus on the right part of the project, but ChatGPT will also include text surrounding it. This all sounds like it will use a lot of input tokens. It's unclear how OpenAI plans to branch this feature out to other apps that are not compatible with Apple's screen reader. Anthropic, one of OpenAI's competitors, released an AI system that analyzes screenshots of a user's desktop to understand and use other apps. To be frank, Anthropic's approach leaves a lot to be desired in its current state: it's slow and makes a lot of mistakes. However, it's a more general purpose version of an AI agent that doesn't rely on APIs, and can do more than just read text in another window. "This isn't meant to be an agent, it's a way to collaborate with coding tools to start, and there will be more tools coming soon" said OpenAI desktop product lead Alexander Embiricos in a briefing with TechCrunch. "On the side of agents, I think this is a really key building block. This idea that ChatGPT understands or can work with all the content that you have so that it can help with it." This step towards agents is especially notable given recent reports that OpenAI is nearing the release of a general purpose AI agent, codenamed "Operator," according to Bloomberg. The tool is expected to arrive in early 2025, and would rival other early attempts at general purpose AI agents, such as Anthropic's Computer use or Google's reported "Jarvis" agent. OpenAI is first releasing these features on MacOS, shortly before Apple launches an integration with ChatGPT in December. It's unclear when Work with Apps will come to Windows, the operating system created by OpenAI's largest backer, Microsoft.

ChatGPT App for Windows Now Available to Everyone

Although ChatGPT has long been available on the web, the Windows-based app stands out by letting you open a "companion window" on your PC. This allows you to easily use the AI chatbot alongside any other Windows programs -- even if you don't have a paid account. "It's a little window you can pull up by pressing Alt + space," OpenAI product developer Alex Embiricos said in a briefing with journalists. "It's really easy to start a new chat without breaking your flow, pick up where you left off, or ask follow-up questions." The app contains many of the same features found in the web-based ChatGPT, including ChatGPT search and Advanced Mode. However, both functions are only available to those with ChatGPT Plus, which costs $20 per month. Still, when we tried the program today, the Windows ChatGPT app gave us a preview of the Advanced Mode for over 10 minutes. In addition, the Windows ChatGPT app can take screenshots, giving users an easy way to feed images to the AI chatbot, in addition to the normal upload photo function. Users can also customize a hotkey to trigger the companion window. For Apple users, OpenAI is also upgrading the ChatGPT app for macOS, which became widely available to all users in June. The big improvement is that OpenAI is giving the app the ability to read computer code from third-party apps. The feature is meant to address how many macOS users felt they were constantly copying and pasting text from third-party apps to ChatGPT, Embiricos said. "For example, instead of copying and pasting code, you can pair ChatGPT with an IDE (Integrated Development Environment) or terminal, and then when you're asking questions, ChatGPT can look at the content in the app to better answer your questions," he added. For now, the company has limited the function to a small batch of coding tools, but the goal is to support a wide range of apps over time. To protect privacy, the user will need to manually activate the feature and select the data that the ChatGPT app can read. These macOS upgrades are initially only available to ChatGPT Plus and Team users. "Enterprise and Edu users will get access in the next few weeks," according to OpenAI, which says the upgrades will eventually come to the ChatGPT Windows app, too.

ChatGTP for macOS now works with third-party apps

OpenAI launched a native ChatGPT app for macOS earlier this year, which makes it easier for Mac users to interact with the company's AI chatbot. Now OpenAI is releasing a huge update to ChatGPT on Mac, which adds integration with third-party apps. With the update, users can ask ChatGPT to read and interact with on-screen content in specific apps. In this first version, integration with third-party software works with developer tools such as VS Code, Terminal, iTerm2 and Apple's Xcode. In a demo seen by 9to5Mac, ChatGPT was able to understand code from an Xcode project and then provide code suggestions without the user having to manually copy and paste content into the ChatGPT app. Users can even interact with more than one app at the same time, which is very useful for working with developer tools. According to OpenAI, the idea is to expand integration to more apps in the future. For now, integration with third-party apps is coming exclusively to the Mac version of ChatGPT, but there's another catch. The feature requires a paid ChatGPT subscription, at least for now. ChatGPT Plus and Team subscribers will receive access to integration with third-party apps on macOS starting today, while access for Enterprise and Education users will be rolled out "in the next few weeks." OpenAI told 9to5Mac that it wants to make the feature available to everyone in the future, although there's no estimate of when this will happen. For privacy reasons, users can control at any time when and which ChatGPT apps they can interact with. It's worth noting that with macOS 15.2, which is currently in beta, Apple is adding the promised ChatGPT integration to Siri - which lets users ask questions related to the content they're seeing on the screen. However, this integration doesn't interact with specific apps yet. You can download the ChatGPT app for macOS from OpenAI's website. It's available for free, while ChatGPT Plus subscribers can sign in and access their full account. On a related note, OpenAI is also making the ChatGPT Windows app available to free users starting today.

I use AI every day and giving ChatGPT access to apps is the biggest AI upgrade of the year

OpenAI first unveiled its macOS ChatGPT app in May and apart from the addition of Advanced Voice a few weeks ago, there wasn't much it could do that you couldn't do on the web. But the addition of a new 'app view' feature, we're seeing the true value of having a desktop app. Revealed on Thursday, the updated ChatGPT app for macOS is now able to see the contents of certain apps as you interact with them. Currently limited to developer tools like Xcode and Visual Studio Code, company insiders have told me that it will be able to interact with those applications in the future, essentially allowing you to make changes by talking to ChatGPT and letting it handle the rest. This is one of the most important upgrades to any AI tool this year and it had stiff competition. So far this year we've had powerful new reasoning models, an early computer use concept from Anthropic, and the emergence of natural human-like voice assistants such as Hume AI, GPT-4o dvanced Voice and Gemini Live. That's before we get into the updates for the best AI image generators and best AI video generators. But I stand by my assertion. Being able to interact with apps on your computer using nothing but natural language prompts is a game-changing moment for human-computer interaction. The new updated app for macOS also comes with a new user interface that puts the 'app connection' and 'model selection' in a new menu tab above the text entry box. You can use this new app feature to have it review code you've written, or even identify issues in the terminal. If coding isn't your thing ChatGPT also has access to TextEdit, Apple's simple but powerful text editor, and you could use this to write very long text-based content and have ChatGPT review it. The true value isn't in what it can do now (although it is useful if you write code), but in what it means for the future. Imagine having a Zoom meeting and ChatGPT being able to see the contents of the call and offer live tips on how to respond or interact meaningfully. Another potentially useful area is in gaming. Picture the scenario: You are in a game of Fortnite and ChatGPT is running in the background. It watches your gameplay and can alert you, in real-time, to any potential threats or offer tips on what to build. I was able to use ChatGPT's ability to see Xcode to create a fully functional iPhone 'endless story' app where the user enters an idea and an AI creates a story for them that they steer themselves by picking options. It took 25 minutes including troubleshooting. The next evolution of the feature will be to have ChatGPT directly interact with apps. This could be a turning point where everyone becomes a developer. It will also make playing games much more fun as the AI will be able to potentially interact with you in-game. You'd be able to ask ChatGPT to come up with a fun game for iPhone -- for argument let's say Flappy Penguin -- and the AI will be able to write the code, open Xcode, implement its code suggestions and even handle sending it to Apple for inclusion in the app store. Your involvement is the initial idea and any refinements -- all done using natural language. That is some way off and if we reach that point it is more likely you'd talk to Advanced Voice and have it handle the code and functionality in the background, presenting you with a complete app and report on the screen. Voice is the future of how we interact with machines.

OpenAI Launches ChatGPT Desktop Version, Mirroring Microsoft's Copilot

ChatGPT can now work with different apps on macOS and Windows desktops, OpenAI announced on X on 15 November. This marks the company's first direct attempt at computer vision and agent control. This early beta update claims to let ChatGPT examine coding apps to provide better answers for Plus and Team users. It not only assists with codes like VS Code, Xcode, Terminal, and iTerm2 but also talks to its users (through its voice assist feature), lets them take screenshots, upload files, and search the web (through SearchGPT). As reported earlier, Anthropic also made Claude Artifacts available to all users on iOS and Android, allowing anyone to create apps easily without writing a single line of code. A ChatGPT feature that becomes highly beneficial in desktop use is asking anything. Users can select any section of any document and open ChatGPT to ask for meanings, explanations, and feedback. This is a desktop implementation of ChatGPT's most evident function. This development follows the discussions from a day ago about OpenAI's agent, 'Operator,' which is to be released in January 2025. Rowan Cheung, founder of 'The Rundown AI,' speculates that the next step beyond this would be to allow ChatGPT to control and see desktops as an agent. In October this year, Microsoft released its 'Copilot Vision' to transform autonomous workflows with Copilot. According to Microsoft, these autonomous agents would be the new 'apps' for an AI-driven world, executing tasks and managing business functions on behalf of individuals, teams, and departments. Meanwhile, the company also introduced ten new autonomous agents in Dynamics 365, to automate processes like lead generation, customer service, and supplier communication for organisations. Following that, Anthropic made a big announcement by releasing its new Claude 3.5 Sonnet which would control computers with the beta feature, 'Computer Use'. The company had reported that the model made significant progress in agentic coding tasks, which involved AI autonomously generating and manipulating code. This approach to Anthropic Claude's computer feature stood out extensively as it didn't rely on multiple agents to perform different tasks; instead, a single agent managed multiple tasks. As compared by AIM earlier, Microsoft integrated Copilot into MS Excel, while Claude directly operated Excel. This called into question the existence of Copilot. OpenAI wasn't behind, even though this move by Anthropic and others (like Google Jarvis, speculated to release this month) had created a stronghold in the AI industry. OpenAI's focus has also shifted to interface from expanding its features. OpenAI entered this race by introducing the Swarm framework, an approach for creating and deploying multi-agent AI systems. It was the missing piece that simplified the process of creating and managing multiple AI agents helping them work together to accomplish complex tasks. Following that, the launch of ChatGPT on desktops was a major step for a pioneer in AI to transform the way this chatbot is used, only to be enhanced by 'Operator' in January. Now, the chatbot will be able to provide answers, be a companion, and assist with daily tasks.

ChatGPT's Windows app is now available to free-tier users - here's what it can do

Previously accessible only to ChatGPT subscribers, now free-tier users can chat with the AI directly from Windows 10 or 11 and so, much more. OpenAI has expanded the reach of its ChatGPT Windows app. Launched a month ago just for subscribers, the app is now freely available to anyone with a ChatGPT account. That means you no longer have to head to the website to chat with your favorite AI. Also: OpenAI is working on a AI agent that can do tasks for you The free app is compatible with Windows 10 and 11. To grab it, browse OpenAI's Download page and click the link for the Windows version under Desktop applications. That takes you to the Microsoft Store to download the program. Run the downloaded ChatGPT Installer.exe file. After the installation, you'll be prompted to sign up or log in with a ChatGPT account. I tried it once with my subscriber account and again with a free-tier account, and the program launched just fine both ways. What will you find in the Windows app? It's similar to the website. You can ask questions, submit requests, and generate content. You're able to ask the AI to create images, analyze uploaded files, summarize text, access custom GPTs, and much more. Also: I'm a ChatGPT power user - and this is still my favorite productivity feature a month later Paid subscribers can use voice mode to carry on a natural, back-and-forth conversation with ChatGPT. As an introductory bonus though, free users can tap into voice mode for a short period of time each month. The app also syncs with your overall ChatGPT activity, so you can continue a conversation or view a past chat from the desktop app, mobile app, or website. Another cool feature of the Windows app is the ability to use keyboard shortcuts. In the app, click the question mark icon in the lower right and select Keyboard shortcuts. You'll find a host of shortcuts for performing actions, such as opening a new chat, copying the last response, toggling the sidebar, and deleting a chat. Also: How to subscribe to ChatGPT Plus (and 7 reasons why you should) Like any Windows app, you can add the ChatGPT program to your desktop or Taskbar for quick access. That makes it more convenient than having to browse the website whenever a question pops into your head. The ChatGPT app for MacOS isn't standing still, either. The Mac version will now work with apps on your desktop. Courtesy of a new beta version of the app, ChatGPT Plus and Team users can even tell the AI to look at the content in coding apps to help them in their work.

OpenAI launches ChatGPT desktop integrations, rivaling Copilot

Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More When OpenAI released desktop app versions of ChatGPT, it was clear the goal was to get more users to bring ChatGPT into their daily workflows. Now, new updates to Mac OS and Windows PC versions encourage users to stay in the ChatGPT apps for most of their tasks. Some ChatGPT on Mac OS users can now open third-party applications directly from the app. ChatGPT Plus and Teams subscribers -- with ChatGPT Enterprise and Edu users following soon after -- can access VS Code, Xcode, Terminal and iTerm2 from a dropdown. This kind of integration calls to mind GitHub Copilot's integration with coding platforms announced in October. Alexander Embiricos, product lead with the ChatGPT desktop team, said one of the biggest user behaviors the company saw was copy-pasting text or code generation with ChatGPT to other applications. Embiricos was the CEO of Multi, a screen sharing and collaboration startup acquired by OpenAI in June. "We wanted to start integration with [integrated development environments] IDEs because we know a lot of our customers are developers, as we were seeing a lot of copy-pasting text-based material from the app to other platforms," Embiricos said. He added that OpenAI wanted to focus on privacy while building the integrations, so the third-party apps would only open manually. Users can begin coding with ChatGPT and choose VS Code from the app. Once launched, VS Code will open with the same code that they were working on. Embiricos said theoretically, people can have multiple third-party apps open while using ChatGPT on Mac. Right now, third-party app integration is only available on Mac OS, but Embiricos said PC users will also get the feature eventually. OpenAI also plans to expand the number of apps in the future. Windows PC is not left behind The Windows PC version of the ChatGPT desktop app will now be available for download to all ChatGPT users, following the limited release to subscribers. Along with expanding the user base, OpenAI updated the PC app with access to Advanced Voice Mode and screenshot capabilities. Embiricos said customers have asked them to use Advanced Voice Mode on desktop for a while, so they wanted to focus on the feature for the PC app. The screenshot capability will also take advantage of some specific features in Windows machines, which will let users choose which windows to take a photo of. "ChatGPT can understand what you're describing to it, of course, but if you add a photo to your chat, its responses are richer, and we see a lot of users copy-pasting photos into ChatGPT so adding a screenshot option makes that easier," Embiricos said. Many of the features in the Mac OS desktop app will also come to PC, but Embiricos noted that the team focused on making the PC app more widely available first. Interfaces are the new battle ground Chat interfaces like ChatGPT proved incredibly useful to a variety of users, but before the advent of desktop versions, people had to go to a website to generate text or code or photos and have to bring chat responses to whichever application they're doing actual work with. So it's no surprise that companies like OpenAI want to capture more of their customer base by bringing their workflows closer to their interface. GitHub made this possible with its integrations with VS Code and Xcode. Anthropic's Claude, while not integrated with third-party apps, created Artifacts so users don't have to go elsewhere to see what their generated webpage looks like. OpenAI followed suit with Canvas, which functions similarly. Meanwhile, Amazon Web Services (AWS) just made its Q Developer AI assistant integrated into popular IDEs Visual Studio Code and JetBrains as an in-line suggestions and code completion add-on, allowing them to highlight chunks of their code and type instructions directly into the LLM without toggling over to another screen. App integration is nothing new for software, as many companies often work together to bring services to where users are. For example, Slack includes apps from Zoom, Atlassian, Asana, and Google that people can call up within a chat window.

OpenAI's ChatGPT for Mac Now Works With Xcode

The ChatGPT app for Mac is now able to integrate with coding apps like Xcode, VS Code, TextEdit, and Terminal, simplifying workflows where developers copy and paste their code from a coding app into ChatGPT. When ChatGPT is given permission to interact with an app like Xcode through a new Work with Apps feature, a selection of code can be sent directly to ChatGPT alongside a prompt. TechCrunch had a demo of the feature, and described how it works: In a demo with TechCrunch, an OpenAI employee opened the ChatGPT app and an Xcode environment containing a simple project modeling the solar system - although it was missing the Earth. The employee selected an Xcode tab within ChatGPT, which tells the AI chatbot to look at the app, and prompted the chatbot to "add the missing planets." The chatbot was able to complete the task, writing a line of code to represent the Earth that matched the rest of the project's format. Back in October, GitHub brought Copilot integration to Xcode, with Copilot providing coding assistance right in the app. ChatGPT's integration is not that deep, and it is not able to write code in Xcode. ChatGPT is instead using the macOS Accessibility API for screen readers that allows apps to read text, which also means that it cannot interpret images or videos. The new ChatGPT for Mac feature is available for ChatGPT Plus and ChatGPT Teams users starting today, with Enterprise and Edu support coming in the near future. Going forward, OpenAI plans to bring this integration to other apps.

ChatGPT Can Now See Your Screen on macOS But There is a Catch

Dubbed "Work with Apps", the feature is rolling out to paid users including ChatGPT Plus, Enterprise, and Education users. OpenAI has updated its ChatGPT desktop app for macOS and brought a new feature called "Work With Apps" in beta. It can read the content on your screen and helps you generate accurate answers by understanding the context. Keep in mind that it's not a full-fledged screen-sharing feature with ChatGPT as promised earlier, but limited to coding apps right now. The ChatGPT app on macOS can now see the content on compatible applications such as Xcode, TextEdit, iTerm, Terminal, VS Code, and other coding apps. To use it, open the compatible app and launch the ChatGPT app. You will see a "Work With Apps" button in the chat bar. Click on it and select the coding application. You can now start prompting ChatGPT and ask contextual questions. You can also select lines in your code editor and ChatGPT will focus on those lines. To deliver this feature, ChatGPT uses macOS Accessibility API. You can enable or disable permission anytime you want. The feature is currently available to ChatGPT Plus, Enterprise, and Education users. It's not clear when it will arrive on the Windows version of ChatGPT. Apart from that, make sure to update the ChatGPT app on macOS to version 1.2024.310 or later. Bear in mind that your interactions with ChatGPT while working with coding apps may be used to train AI models. If you are not comfortable with it, you can disable mode training on ChatGPT. So are you excited about the real-time ChatGPT coding companion or do you still prefer Cursor or other AI coding editors? Let us know in the comments below.

ChatGPT's Windows desktop app is now available to free users, too

Previously for paid subscribers only, free users can now download and use the app from the Microsoft Store. ChatGPT and other similar AI chatbots are becoming a bigger part of everyday life for many people. Though a Windows app for ChatGPT has been available for some time, it's only been for those who have ponied up for a premium plan -- until now. The Windows app for ChatGPT is now available to all, just like the web and mobile apps. You can download it from the Microsoft Store. Poking around a bit in the Windows app, it seems more or less the same as the interface I've tested on my Android phone, though of course in Windows it's easier to input larger amounts of text or submit images for scanning. It has the popular conversation mode along with a handful of digital voice options, but it's just as restrictive as it is elsewhere -- I hit the freebie interaction limit in just a few minutes. (And just in case my editor is looking over my shoulder: don't worry, I'm only testing the app out. I promise this news post was written with my fleshy, human fingers.) Those who do spring for ChatGPT's premium service, which starts at $20 per month for individual users, will likely find the Windows app far more useful. While it's largely the same as the web interface, having a dedicated window on your desktop will be a boon to those who integrate it into their workflows. Whether or not it's worth paying for a premium AI chatbot? Well, that'll depend on how you use it. And not for nothing, it's another point for OpenAI to tick in competition with Microsoft's home-grown AI product, Copilot. Anecdotally, ChatGPT is much more positively received by general users, whereas Microsoft is more interested in integrating Copilot into core Windows features, from the taskbar to Office to Paint.