ChatGPT 'Work with Apps' feature: How to use it to code faster and edit notes
OpenAI updated its 'Work with Apps' feature on macOS recently. The new upgrade is available with version 1.2025.057, and to access it, you need to download the ChatGPT for macOS application.
If you're not familiar with what the 'Work with Apps' functionality on macOS brings to ChatGPT, it essentially allows the AI to read and edit content directly within your coding applications or text editors like Notes. This integration enables more tailored and context-aware responses based on your work, helping you do things quickly.
To begin with, you might be wondering which applications this ChatGPT feature supports. It includes text editors like Apple Notes, Notion, TextEdit, as well as coding-specific applications like Xcode, Script Editor, VS Code, Terminal, iTerm, Warp, and Prompt.
To get started, ensure the ChatGPT app is open in the background. And then press Option + Space alongside the app you want to work with. For example, if you have Xcode or the Apple Notes app open, simply press Option + Space. The ChatGPT window will pop up, automatically detecting the application. It will indicate this with a tag like 'Work with Notes' Tab or 'Work with Xcode,' depending on your app.
You can then prompt ChatGPT accordingly, and it will be context-aware.
Before you start, you must enable ChatGPT's permissions in Accessibility Settings on your Mac. This requires authentication and password entry.
For integrated development environments (IDEs), ChatGPT can even edit files directly, removing the need for any copy-pasting. Also, there is also an option to automatically apply edits, making the coding process even faster.
OpenAI confirms that content accessed through Work with Apps is part of your ChatGPT account history and may be used to enhance its AI models. However, you have the option to toggle the "Improve the Model for Everyone" setting if you do not wish your data to be used for this purpose. Alternatively, you can use the Temporary Chats feature, which ensures your data is not saved in your ChatGPT account history.
MOBILE FINDER: iPhone 16 LATEST Price, Specs And More
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Time of India
an hour ago
- Time of India
Yageo says it will protect technology if Shibaura purchase succeeds
By Wen-Yee Lee and Makiko Yamazaki TAIPEI/TOKYO: Taiwan's Yageo said it will implement strict controls to prevent technology from leaking if it succeeds in acquiring Japan's Shibaura Electronics , responding to concerns in Japan over what the deal could mean for national security. Chairman Pierre Chen told reporters in Taipei on Saturday that the company will meet with Shibaura in mid-June in Tokyo to discuss potential cooperation. Yageo, the world's largest maker of chip resistors, launched an unsolicited tender offer for Shibaura in February, seeking full control of the Japanese firm, which specialises in thermistor technology . Yageo offered to buy Shibaura at 4,300 yen per share, valuing the company at more than 65 billion yen ($450 million). Spurning Yageo's overture, Shibaura tapped Japanese components supplier Minebea Mitsumi as a white knight. Minebea and Yageo entered a bidding war, with the latter now offering 6,200 yen. The stock closed at 6,100 yen on Friday. "Our strategy is to inject resources and strengthen R&D for advanced technologies. We're also preparing to make larger investments to expand their facilities in Japan," Chen said. Asked about Japan's national security concerns, he said: "We will implement strict controls to ensure technology does not leak." Unsolicited takeovers were once rare in Japan, where companies often mounted elaborate defences. The Japanese industry ministry's M&A guidelines in 2023 cracked down on what it considered excessive defence tactics, de-stigmatising unsolicited buyouts and leading some of such deals to succeed. Chen said that negotiations with Japan's Ministry of Economy, Trade and Industry had been going smoothly. He said that if Yageo acquires Shibaura, the deal would address a gap in its portfolio of thermistors, making Yageo's offerings more complete for global customers and helping Shibaura expand its access to markets outside of Japan. Yageo said it aims to ease the burden of managing smaller component suppliers for its major clients, including Apple and Nvidia, by offering more comprehensive product portfolios and solutions. Yageo is also the world's number three manufacturers of multilayer ceramic capacitors and provides key components used in Apple's iPhones, Nvidia's AI servers, and Tesla's electric vehicles.
Time of India
2 hours ago
- Time of India
For some recent graduates, the AI job apocalypse may already be here
HighlightsUnemployment for recent college graduates has risen to 5.8%, with a notable increase in job displacement due to advancements in artificial intelligence, particularly in technical fields like finance and computer science. Many companies are adopting an 'AI-first' approach, with some executives reporting a halt in hiring for lower-level positions as artificial intelligence tools can now perform tasks that previously required human employees. Dario Amodei, Chief Executive Officer of Anthropic, has predicted that artificial intelligence could eliminate half of all entry-level white-collar jobs within the next five years. This month, millions of young people will graduate from college and look for work in industries that have little use for their skills, view them as expensive and expendable, and are rapidly phasing out their jobs in favour of artificial is the troubling conclusion of my conversations over the past several months with economists, corporate executives and young job seekers, many of whom pointed to an emerging crisis for entry-level workers that appears to be fuelled, at least in part, by rapid advances in AI capabilities. You can see hints of this in the economic data. Unemployment for recent college graduates has jumped to an unusually high 5.8% in recent months, and the Federal Reserve Bank of New York recently warned that the employment situation for these workers had 'deteriorated noticeably.' Oxford Economics, a research firm that studies labour markets, found that unemployment for recent graduates was heavily concentrated in technical fields like finance and computer science, where AI has made faster gains. 'There are signs that entry-level positions are being displaced by artificial intelligence at higher rates,' the firm wrote in a recent report. But I'm convinced that what's showing up in the economic data is only the tip of the iceberg. In interview after interview, I'm hearing that firms are making rapid progress toward automating entry-level work and that AI companies are racing to build 'virtual workers' that can replace junior employees at a fraction of the cost. Corporate attitudes toward automation are changing, too — some firms have encouraged managers to become 'AI-first,' testing whether a given task can be done by AI before hiring a human to do it. One tech executive recently told me his company had stopped hiring anything below an L5 software engineer — a mid-level title typically given to programmers with three to seven years of experience — because lower-level tasks could now be done by AI coding tools. Another told me that his startup now employed a single data scientist to do the kinds of tasks that required a team of 75 people at his previous company. Anecdotes like these don't add up to mass joblessness, of course. Most economists believe there are multiple factors behind the rise in unemployment for college graduates, including a hiring slowdown by big tech companies and broader uncertainty about President Donald Trump's economic policies. But among people who pay close attention to what's happening in AI, alarms are starting to go off. 'This is something I'm hearing about left and right,' said Molly Kinder, a fellow at the Brookings Institution, a public policy think tank, who studies the impact of AI on workers. 'Employers are saying, 'These tools are so good that I no longer need marketing analysts, finance analysts and research assistants.'' Using AI to automate white-collar jobs has been a dream among executives for years. (I heard them fantasising about it in Davos back in 2019.) But until recently, the technology simply wasn't good enough. You could use AI to automate some routine back-office tasks — and many companies did — but when it came to the more complex and technical parts of many jobs, AI couldn't hold a candle to humans. That is starting to change, especially in fields, such as software engineering, where there are clear markers of success and failure. (Such as: Does the code work or not?) In these fields, AI systems can be trained using a trial-and-error process known as reinforcement learning to perform complex sequences of actions on their own. Eventually, they can become competent at carrying out tasks that would take human workers hours or days to complete. This approach was on display last week at an event held by Anthropic, the AI company that makes the Claude chatbot. The company claims that its most powerful model, Claude Opus 4, can now code for 'several hours' without stopping — a tantalising possibility if you're a company accustomed to paying six-figure engineer salaries for that kind of productivity. AI companies are starting with software engineering and other technical fields because that's where the low-hanging fruit is. (And, perhaps, because that's where their own labour costs are highest.) But these companies believe the same techniques will soon be used to automate work in dozens of occupations, ranging from consulting to finance to marketing. Dario Amodei, Anthropic's CEO, recently predicted that AI could eliminate half of all entry-level white-collar jobs within five years. That timeline could be wildly off, if firms outside tech adopt AI more slowly than many Silicon Valley companies have, or if it's harder than expected to automate jobs in more creative and open-ended occupations where training data is scarce.
Hindustan Times
4 hours ago
- Hindustan Times
Unnoticed, UAE may have curated workable concept for AI regulation
On a recent trip (no secret, to attend the keynote and briefings at Google I/O a few weeks ago), my ears caught the sound of a rather interesting podcast aboard an Emirates A380. Usually these tend to be about food or lifestyle — though the one with Kilian Hennessy is exceptional too — but to have one in which United Arab Emirates' Minister of State for AI, Omar Al Olama talks about his vision of artificial intelligence (AI) regulation, is quite extraordinary. Also because he is the world's first minister for all things AI, appointed in October 2017. His vision is a bit different from everything I've heard from regulators in many countries, including India. Instead of regulation being structured as a restriction, Al Olama's approach lies in a philosophy that hopes to balance innovation with responsibility. Rather than rushing to implement what may prove to be restrictive regulations, since its still early days considering the contours of the AI space evolve almost every other day, the UAE has positioned itself as what Al Olama calls 'a responsible AI nation.' There are five key tenets to UAE's approach to AI, a working blueprint that many other countries could do well to look closely at. First, the UAE aims to become a global leader in AI by 2031. Secondly, there is belief that AI will be a 'new lifeblood' for both governments and the private sector, transforming various industries. Third, the country envisions a future where individuals have multiple digital assistants, potentially reaching PhD-level capabilities. Fourth, UAE is actively seeking international partnerships and investments to strengthen its position as a global technology hub. And lastly, there is a willingness to play a key role in the framing of internationally applicable rules to ensure AI security and safety, as well as build frameworks for protection of personal data and privacy. The fact is simple, Al Olama knows what he is talking about. As far back as in 2019, during a keynote speech at Orchestrating Winning Performance in Dubai, he noted, 'Everyone is talking about AI. Whoever is going to lead in the Artificial Intelligence race will lead the future. This technology will change the world.' Fast forward to 2025, and we have AI which undoubtedly is part of many a workflow for businesses and enterprises, and individuals are learning to trust AI tools more slowly but steadily (whether being careful enough is a debate for another day). In the past few years, UAE has silently gone about meaning business. But there is a demographic change that needs to happen, sooner rather than later, if the country has to achieve its mission. According to the latest UNESCO data, 0.19% of the UAE's population are working as full time researchers in science, technology, and innovation. In contrast, Korea, which leads this metric, clocks in with 0.69%, followed by Singapore (0.66%) and Norway (0.59%). The US finds 0.42% of its population in these roles, while India clocks in with 0.02% (important to note — this percentage is looking worse than it may be, owing to a much higher comparative baseline population number). A few days ago, the UAE released a new Arabic-language AI model, called Falcon Arabic, in an effort to make AI locally relevant and accessible. This is something experts too have talked about. India is working on its own LLM, or large language model. As is Singapore. These are just some examples, in the search of an AI that understands local context and sensitivities more than a global model perhaps might. Falcon Arabic has been trained on a dataset spanning Modern Standard Arabic and regional dialects, and Abu Dhabi's Technology Innovation Institute (TII) claims this model matches the performance of models up to 10 times its size. This model may still find it difficult to match up to the likes of Google Gemini, China's DeepSeek and OpenAI as well as Anthropic's fast evolving GPT and Claude models respectively, but it is a start nonetheless. There is an understanding that isolation, and go-it-alone doesn't work. OpenAI and the UAE are working together for something called the Stargate UAE, a 1-gigawatt AI supercomputing cluster in Abu Dhabi, as part of the AI company's 'OpenAI for Countries' initiative. American tech companies like Oracle, Nvidia, Cisco, and SoftBank, as well as G42, an Emirati artificial intelligence firm, are all part of various AI projects. But it's likely you may have seen excitable headlines about all UAE residents being given free subscriptions to ChatGPT Plus — because that gets the citizens involved. The US sees this as an opportunity too. Tech companies in the US, presently develop the world's most advanced semiconductor chips. The other side of that coin has the UAE that can offer abundant, low-cost energy that is needed to power enormous AI data centres. Back to the regulation approach for a moment. The European Union has pursued comprehensive legislation through the AI Act, which categorises AI systems by risk levels and imposes strict requirements on high-risk applications. They have the GDPR as an example that their regulation methods are thorough, as it is the case here too. But then again, it can also be overly complex for tech companies to navigate, and could stifle innovation particularly for companies with limited resources. The United States has thus far taken a more fragmented approach, with a lack of comprehensive federal legislation, but that could change once the Trump administration gets down to regulating AI. India currently doesn't have rules that regulate AI just yet, but the country is in the process of formulating and implementing policy frameworks to govern various aspects of AI. The blueprint is there for other countries to look closely at, but the UAE has an advantage of geographical size, its political structure and economic positioning that may be difficult for larger countries to work with — getting a consensus may not be as easy there, as would geographic, economic and human limitations that may come into play. But AI regulation is around the bend, just that we may have differing approaches for the time being. (Vishal Mathur is the Technology Editor for HT. Tech Tonic is a weekly column that looks at the impact of personal technology on the way we live, and vice-versa. The views expressed are personal.)
