Latest news with #Operator
The Verge
2 days ago
- Business
- The Verge
I sent ChatGPT Agent out to shop for me
Think of OpenAI's new ChatGPT Agent as a day-one intern who's incredibly slow at every task but will eventually get the job done. Well… most of the job. Or… at least part of it. Usually. It's been one day since OpenAI debuted ChatGPT Agent, which it bills as a tool that can complete a wide range of complex, multi-step tasks on your behalf using its own 'virtual computer.' It's a combination of two of the company's prior releases, Operator and Deep Research. The Verge forked over the $200 for a one-month subscription ChatGPT Pro, since OpenAI announced that higher-than-expected demand for ChatGPT Agent will delay its rollout to Plus and Team users. Our take: It's a step forward in the world of AI agents, but it's sluggish, not always reliable, and can be glitchy. By typing '/agent,' I entered what OpenAI calls Agent Mode, and it immediately suggested five example tasks: Find a top-rated coffee grinder under $150, review rare earth metals coverage from The Wall Street Journal, create a Google Maps list of the best bakeries in Copenhagen, find a vintage 'Japanese-style' lamp on Etsy for less than $200, and check Google Calendar to create a date night for next week. I tried the Etsy lamp option. By clicking the example task, it filled out a detailed prompt for me in the text window: 'Find a Japanese-inspired vintage-style samsara lamp on Etsy priced under $200 with free shipping. Prioritize high-quality photos, seller ratings, and listings marked as ready to ship. Add the best 5 options to my cart and provide a URL for each for me to compare.' A small window popped up to detail the agent's tasks one-by-one (not the chain-of-thought reasoning, just the task it was currently working on at the time). It worked on the Etsy lamp task for 50 minutes, and the step-by-step tasks included 'thinking,' setting up its desktop, navigating to Etsy to search, waiting for the site to load, pressing Enter for search results (yes, it really gave me a true play-by-play), filtering the search for a vintage lamp (keep in mind the original prompt said 'vintage-style,' not 'vintage' specifically), setting the price filter to $200, checking shipping details for items, and more. Another wrinkle: ChatGPT Agent said, 'I added all five lamps to your Etsy cart (the cart shows five items totaling around $825). When you're ready to review or purchase them, just go to your cart on Etsy to compare them side by side.' But it didn't do that – I went to Etsy on my own computer and there was nothing in my cart. That's because ChatGPT Agent doesn't control my own browser or have access to my logins, so it possibly added some lamps to the cart of a virtual PC that I can't access. It did send me individual URLs, so I could manually put them in a cart if I wanted, but the fact remains that the agent said it did something that it clearly did not. And, of course, ChatGPT Agent is incredibly slow. That's not a secret. For many of ChatGPT Agent's use cases, including everyday consumer tasks, a human could do it much faster. According to OpenAI, ChatGPT Agent is an assistant that works in the background on tasks you'd rather someone else perform while you do something you do want to do instead. In a private demo and briefing Wednesday with OpenAI employees Yash Kumar and Isa Fulford — product lead and research lead on ChatGPT Agent, respectively — Kumar said their team is more focused on 'optimizing for hard tasks' than latency and that users aren't meant to sit and watch ChatGPT Agent work. ChatGPT Agent is incredibly slow. That's not a secret. 'Even if it takes 15 minutes, half an hour, it's quite a big speed-up compared to how long it would take you to do it,' Fulford said.. 'It's one of those things where you can kick something off in the background and then come back to it.' Another thing I wanted to test: how ChatGPT Agent acts when you ask it to move your money around. The answer: It won't do it, but it's majorly glitchy about it and seems not fully secure. When I asked OpenAI's Kumar on Wednesday whether the tool would be permitted to work on financial transactions and the like, he said those task categories have been restricted 'for now' and that an additional safeguard called Watch Mode means that for certain categories of websites, the user must not navigate away from the ChatGPT tab (essentially making the user oversee the agent) for security reasons. I prompted the agent like this: 'I want to save more money. Log into my bank account and set up an automatic transfer to my savings every month.' At first, I got a bizarre error message with a string of numbers in red. When I asked again, it said, 'I'm sorry, but I can't help with setting up an automatic transfer between accounts.' I then wrote, 'Why not? I'm giving you permission.' I got the same red-text, long-string-of-numbers error message as before. Afterward, it said, 'I'm sorry, but I can't assist with setting up transfers or other banking account management tasks.' At first, I got a bizarre error message with a string of numbers in red. When I pressed it on which financial transactions it's allowed to handle, ChatGPT Agent said it was able to assist with 'everyday consumer purchases' like groceries, household goods, and travel bookings, which handle 'standard checkout flows' rather than 'sensitive banking actions.' But it clarified it can't help with 'high-stakes' financial to-dos like transferring money, opening bank accounts, or buying regulated goods like alcohol and tobacco. Since ChatGPT Agent can assist with buying things, but not moving money around, I tried something else: Asking it to buy flowers for my friend Alanna in Colorado. I buy flowers a lot — that's what happens when your two best friends live in different states and you want to be present for big milestones even when you can't fly there. The online flower-delivery market can be a huge headache: Prices and bouquet sizes vary greatly depending on the service or florist, and reliability varies depending on whether you're ordering directly from a local florist or a big-box nationwide site. It's something I get tired of researching on my own, and sometimes I just end up buying whichever bouquet I have selected when I run out of steam, even if it's not the best one. So, I reasoned, it was the perfect job for an AI agent. I told ChatGPT Agent, 'I want to buy flowers for my friend who lives in Colorado. Check the delivery sites — it's fine to be delivered Saturday but no later. Find the cheapest and biggest bouquet options for me to review.' I settled in for a long wait. Luckily, I had a call to join anyway. It asked which area of Colorado she lived in, and I answered. When I glanced over to check in, I noticed ChatGPT Agent was heavily relying on a Forbes article of 'best flowery delivery services 2025' for its next steps, as well as a piece from Good Housekeeping. I navigated away from the tab, and when I came back, the conversation was gone and didn't appear in my chat history. So I asked the question again, worded in exactly the same way, and settled in for another wait. At this point, the agent answered pretty immediately with a list of options, maybe because it had already done the research (although that research and chat didn't appear in my history). I was impressed with the write-up. ChatGPT Agent gave me four options with price ranges and sometimes weighed in on the apparent size of the bouquet or expected delivery times. It also offered the advice that local florists are generally more reliable (true, in my experience). It then told me, 'Would you like me to help you place an order with any of these options, or preview specific bouquet designs or photos?' I picked one of the options it gave me — a local florist with hand-assembled bouquets — and asked it to help me pick a bouquet from that florist and place the order. That's when we ran into some issues. ChatGPT Agent said, 'I can't directly access Vintage Magnolia's website unless you provide the exact URL you're seeing — but I can guide you through how to place the order and help you pick a bouquet!' The weird part: Obviously ChatGPT Agent was the one to tell me about that florist and its website, and it had clearly accessed it before. It had also just offered to help me place the order. Another glitch. But its answer did include bouquet options (no photos, but descriptions). I picked one and asked it to place the order for me. It said, 'I can't place the order directly, but I'll walk you through the simple steps to order … and help you craft the perfect message.' It can easily automate the more intimate and fun parts of the process, like picking a specific bouquet or writing a heartfelt note. I'm confused at this point: One of the main selling points of ChatGPT Agent, touted by OpenAI, is that it can place orders for you, from online shopping to ordering groceries for a four-person family breakfast (in fact, that was one of their example use cases in their marketing materials). I pressed ChatGPT Agent on the subject. It told me, 'I can't actually place orders directly — I don't have payment access or the ability to log into third‑party sites.' When I told it it didn't need to log in, it said it can't enter my billing or payment details, submit an order form on my behalf, or 'access or control external websites, even in guest mode.' ChatGPT Agent can be impressive with analysis, weighing options, and guiding you through actions, but it doesn't seem to be able to always deliver on what it was built for: Performing those actions for you. It gets tripped up by the fact that it's using its own computer, not yours, and that significantly limits its usefulness. Plus, it can easily automate the more intimate and fun parts of the process (picking a specific bouquet, writing a heartfelt note) but struggles to automate the most frustrating parts (actually filling out delivery details and making the purchase). 'Even with your permission, I don't have the technical ability to act as you on another site — no typing on your behalf, clicking buttons, or filling out credit card forms,' ChatGPT Agent wrote. 'Think of me more as a super-powered assistant who can gather, compare, write, and guide — but not execute transactions.' One of my first jobs in New York was a personal assistant, and I can tell you right now I would've lost my job if I couldn't execute transactions or fill out forms on my boss's behalf. ChatGPT Agent is a step forward for everyday AI use in some ways, but we'll see if it learns to deliver on its promises.
GSM Arena
2 days ago
- Business
- GSM Arena
OpenAI announces ChatGPT Agent – its autonomous AI tool that does tasks for you
OpenAI announced its latest agentic AI called ChatGPT Agent. It combines features from Operator with its ability to interact with websites and ChatGPT's conversational fluency, alongside deep research skills and information synthesis into ChatGPT so it can get work done on your behalf. As OpenAI puts it, 'ChatGPT Agent carries out tasks using its own virtual computer, fluidly shifting between reasoning and action to handle complex workflows from start to finish, all based on your instructions.' So what can it do? You can ask it to automate repetitive work-related tasks like rescheduling meetings, updating spreadsheets or creating presentation slides and research reports. It can also plan and book trips with travel, lodging and activities all from a single prompt or schedule appointments on your behalf. ChatGPT Agent analyzing data and creating a presentation You can link other services and apps like Gmail and GitHub so ChatGPT Agent can find relevant information to your prompts. ChatGPT Agent booking flights and checking Google Calendar ChatGPT Agent uses a new unspecified AI model which was trained on tasks that require multiple tools, including text and visual browsers as well as code terminals. As with past OpenAI releases, ChatGPT Agent will follow a staged rollout and will be available to ChatGPT Pro, Plus, and Team users first. Those users will see a new agent mode in the dropdown menu tools on ChatGPT. Source
TECHx
2 days ago
- Business
- TECHx
ChatGPT Agent Launched to Handle Complex Tasks
Home » Latest news » ChatGPT Agent Launched to Handle Complex Tasks OpenAI launches a ChatGPT agent that handles complex tasks, connects to apps like Gmail and GitHub, and uses tools for multi-step actions via a virtual computer. OpenAI has announced the launch of a new artificial intelligence agent for its popular chatbot, ChatGPT. The update was revealed on Thursday and is now available to users on the Pro, Plus, and Team tiers. The ChatGPT agent is designed to handle complex tasks without constant user input. It builds on OpenAI's earlier agentic features, including Operator, which can interact with websites, and Deep Research, a tool for conducting multi-step research. This launch comes as the Microsoft-backed startup looks to stay ahead in the AI race. Reports show that AI agents are gaining traction across the tech industry. Major companies like Microsoft, Salesforce, and Oracle are investing heavily in similar tools to improve productivity and reduce operational costs. According to OpenAI, the new ChatGPT agent can complete real-world tasks, such as ordering an outfit for an event. It can consider multiple factors like dress code and local weather. This function is made possible through a virtual computer built into ChatGPT. Moreover, the agent allows users to connect third-party applications, including Gmail and GitHub. This enables ChatGPT to access relevant data and perform tailored actions based on the user's prompt. Key capabilities include: Performing multi-step research and transactions Connecting with web apps to retrieve and process information Starting Thursday, users can activate the agentic capabilities from their ChatGPT settings. The company reported that this rollout is part of its ongoing efforts to integrate advanced tools into its chatbot while improving real-world utility. OpenAI did not specify when the feature might expand beyond the current subscription tiers. However, it confirmed that the ChatGPT agent is aimed at making everyday tasks more streamlined and data-driven. Source: Reuters
&w=3840&q=100)
First Post
2 days ago
- Business
- First Post
What is the new ChatGPT Agent that can ‘control' your computer?
ChatGPT Agent is OpenAI's latest Artificial Intelligence tool. The tech firm helmed by Sam Altman claims that ChatGPT Agent goes far beyond being a mere chatbot and uses its own virtual computer to 'think' and 'act'. ChatGPT Agent became available on Thursday (July 17) for subscribers of OpenAI's Pro, Plus, and Team plans. Here's what we know about it read more The software, known as ChatGPT Agent, can undertake a wide variety of computer-based tasks for users. OpenAI has launched a new software for ChatGPT. The software, known as ChatGPT Agent, can undertake a wide variety of computer-based tasks for users. ChatGPT Agent became available on Thursday for subscribers of OpenAI's Pro, Plus, and Team plans. Users simply have to choose 'agent mode' in ChatGPT's dropdown menu to activate it. But what is it? What do we know about it? How does it work? Why is it significant? What is it? OpenAI, which is helmed by Sam Altman, claims that ChatGPT Agent goes far beyond being a mere chatbot. STORY CONTINUES BELOW THIS AD The company says that ChatGPT Agent uses its own virtual computer to 'think' and 'act'. It essentially functions like a personal assistant to which you can delegate tasks. This includes executing code, going to websites, managing your calendar, making meal plans, creating presentations and spreadsheets, and summarising meetings. The company says users can interact with ChatGPT Agent in a 'natural language'. The company in its blog said users can issue commands such as 'look at my calendar and brief me on upcoming client meetings based on recent news' or 'plan and buy ingredients to make Japanese breakfast for four'. ChatGPT Pro subscribers will be allowed 400 queries per month. Meanwhile, ChatGPT Team/Plus users will receive 40 queries per month. Distressing news and traumatic stories can cause stress and ChatGPT Agent uses its own virtual computer to 'think' and 'act'. It will available to ChatGPT Enterprise and Education users later this year. Interestingly, the brains behind ChatGPT agent is an Indian. He is currently in charge of the team behind ChatGPT Agent, Kumar and Isa Fulford, the research lead on ChatGPT Agent, unveiled the software in a demonstration with The Verge. Kumar and Fulford in the demonstration asked ChatGPT Agent to plan a date night for a couple. STORY CONTINUES BELOW THIS AD They also requested that ChatGPT Agent write a research report on Labubus and compare their ascendancy with Beanie Babies. This includes the web browser tool Operator and Deep Research, an analysis tool which can take information from different websites and write a research report. Open AI had described Operator as 'an agent that can go to the web to perform tasks for you'. The model behind ChatGPT Agent, which does not have a name, was trained through reinforcement learning – which is the standard technique for all OpenAI's reasoning models. OpenAI says the model delivers state-of-the-art performance on several benchmarks, according to OpenAI. This includes Humanity's Last Exam in which it scored 41.6 per cent – which is around double of what OpenAI's o3 and o4-mini got on the test. When it comes to the toughest maths tests, OpenAI said ChatGPT Agent hit 27.4 per cent using a terminal that allows it to execute code. STORY CONTINUES BELOW THIS AD The o4-mini, meanwhile, which was considered the top scorer on FrontierMath, netted a mere 6.3 per cent. The company combined teams from both Operator and Deep Research to work on ChatGPT Agent. The team comprised between 20 and 35 people. Why is it significant? Because until now, all the AI chatbots have simply sought to answer questions from users. OpenAI is taking things a step further than its rivals by making ChatGPT Agent more of a personal assistant. Countries and companies across the world are currently in an AI arms race. DeepSeek, a previously little-known Chinese firm, shook up Wall Street and Silicon Valley earlier this year. The Trump administration has vowed to spend $500 billion in the AI race in a project it has dubbed 'Stargate'. OpenAI says users can even instruct ChatGPT Agent while the task is unfolding. 'Likewise, ChatGPT itself may proactively seek additional details from you when needed to ensure the task remains aligned with your goals. If a task takes longer than anticipated or feels stuck, you can pause it, ask it for a progress summary, or stop it entirely and receive partial results. If you have the ChatGPT app on your phone, it will send you a notification when it's done with your task,' says OpenAI in its blog post. STORY CONTINUES BELOW THIS AD However, the team behind the software warns that ChatGPT Agent is still a bit slow – relatively speaking of course. 'Even if it takes 15 minutes, half an hour, it's quite a big speed-up compared to how long it would take you to do it,' Fulford told The Verge. 'It's one of those things where you can kick something off in the background and then come back to it.' OpenAI CEO Sam Altman took to social media to tout ChatGPT Agent's potential. Fulford told Wired she asked ChatGPT agent to order cupcakes for her. 'I was very specific about what I wanted, and it was a lot of cupcakes,' she says. 'That one took almost an hour—but it was easier than me doing it myself, because I didn't want to do it.' For those who worry, ChatGPT Agent also asks for user permission before doing important things such as sending an email or making a booking. The firm has said that it has built many protections into ChatGPT Agent. STORY CONTINUES BELOW THIS AD This includes refusing to work on 'high-risk' tasks such as bank transfers. 'We have built a lot of safeguards and warnings into it, and broader mitigations than we've ever developed before from robust training to system safeguards to user controls, but we can't anticipate everything. In the spirit of iterative deployment, we are going to warn users heavily and give users freedom to take actions carefully if they want to,' Altman said. He recommended that users refrain from giving ChatGPT Agent too much personal information. 'We recommend giving agents the minimum access required to complete a task to reduce privacy and security risks,' he added. Still, Altman took to social media to tout ChatGPT Agent's potential. 'Agent represents a new level of capability for AI systems and can accomplish some remarkable, complex tasks for you using its own computer. It combines the spirit of Deep Research and Operator, but is more powerful than that may sound—it can think for a long time, use some tools, think some more, take some actions, think some more, etc,' Altman wrote on X. STORY CONTINUES BELOW THIS AD 'For example, we showed a demo in our launch of preparing for a friend's wedding: buying an outfit, booking travel, choosing a gift, etc. We also showed an example of analysing data and creating a presentation for work,' he added. With inputs from agencies
Mint
2 days ago
- Business
- Mint
OpenAI unveils advanced ChatGPT agent for seamless task automation
OpenAI has revealed its new and powerful ChatGPT agent, which is designed to automate complex tasks and execute multistep queries from users. This cutting-edge AI agent has started rolling out to ChatGPT's Pro, Plus, and Team users. It is a significant breakthrough in AI assistance, and here's everything about it. Unlike the regular version of ChatGPT that we use currently, which only responds to queries and engages in conversation, this new agent can actively interact with websites and connected apps in real time using a 'virtual computer' environment. It can mimic human actions such as browsing the web, filling out forms, opening links and typing to complete tasks independently. For example, if you want to plan a trip, you just need to enter your preferences and it will do everything. It can suggest places to visit, book a hotel, help with packing for the trip, provide weather information during your planned visit and much more, all without the need to enter multiple queries. ChatGPT already has experimental tools such as Operator and Deep Research. The operator can navigate websites, while Deep Research automates complex information gathering. The new Agent brings the strengths of both of these tools together for seamless task execution and sophisticated reasoning. Additionally, users can connect apps like Gmail and GitHub, allowing the agent to scan emails, access documents,or review code repositories to enhance productivity. OpenAI CEO Sam Altman has highlighted that while the agent is currently in the early preview phase, it has the potential to significantly boost both personal and workplace productivity by taking over repetitive and complex workflows. Importantly, users have full control over the agent and can give permission, interrupt or stop any ongoing task at any time. This launch places OpenAI alongside other leading tech giants investing in AI agents as the future of digital assistants. The arrival of this advanced agent also suggests that the rumoured AI-powered browser could be real and possibly launching soon. There have been reports that OpenAI is working on a browser called Aura, and perhaps this new agent will power that browser.
