Latest news with #ChatGPTPro
Indian Express
4 days ago
- Business
- Indian Express
OpenAI to unveil GPT-5 in August: Here's how it is different
OpenAI is gearing up to introduce its much-awaited GPT-5 model. While CEO Sam Altman has been hinting at a potential early launch, no reports suggest that the new LLM from OpenAI could arrive as early as August 2025. Reportedly, the new model will be launched along with nano and mini versions and API access for developers. The upcoming AI model has been in the making for a long time and has been delayed multiple times. In February this year, the company introduced GPT-4.5 Orion to ChatGPT Pro users. While the company has launched a number of AI models, the launch of GPT-5 has been repeatedly changed owing to safety tests and refinements. On July 19, when OpenAI's experimental reasoning LLM achieved a gold medal-level performance in the International Math Olympiad, CEO Sam Altman took to his X account to share the news. While lauding the company's efforts, he also said that they would be launching GPT-5 soon. Describing the model, Altman said that it was an experimental model that incorporates new research techniques that the company will be using in its future models. 'We think you will love GPT-5, but we don't plan to release a model with IMO gold-level capability for many months,' he wrote. we achieved gold medal level performance on the 2025 IMO competition with a general-purpose reasoning system! to emphasize, this is an LLM doing math and not a specific formal math system; it is part of our main push towards general intelligence. when we first started openai,… — Sam Altman (@sama) July 19, 2025 Murmurs around GPT-5 were heard earlier this month after 'GPT-5 Reasoning Alpha' appeared in the configuration file as shared on X by Tibor Blaho, an engineer. While earlier, Altman had said that GPT-5 will be arriving in Summer 2025, newer reports now suggest that the model will be arriving next month. When it comes to features, GPT-5 is expected to be a significant leap from its predecessors and would come with unified multimodal capabilities that would integrate text, audio, image, and video processing—all of this into one architecture. The model is also reported to feature advanced reasoning capabilities with hybrid architecture for enhanced logical reasoning and problem-solving. The context window is expected to be extended beyond one million tokens in contrast to GPT-4's 128,000 tokens. Other expected features include native Sora integration and advanced Canvas tools. GPT-5 will also be working towards reducing hallucinations substantially. And, this reportedly will be achieved by implementing a chain of thought (CoT) mechanism.
The Verge
18-07-2025
- 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.
Phone Arena
18-07-2025
- Phone Arena
ChatGPT now thinks and acts, and this could be the end… of your to-do list
Receive the latest Apps news Subscribe By subscribing you agree to our terms and conditions and privacy policy ChatGPT can now do work for you using its own computer. Introducing ChatGPT agent—a unified agentic system combining Operator's action-taking remote browser, deep research's web synthesis, and ChatGPT's conversational strengths. — OpenAI (@OpenAI) July 17, 2025 Would you trust an AI agent to take real-world actions for you (like booking, ordering, emailing)? Yes, bring it on! Maybe, with supervision. Only for simple stuff. No way, too risky. Yes, bring it on! 0% Maybe, with supervision. 0% Only for simple stuff. 0% No way, too risky. 0% If you're subscribed to ChatGPT Pro, Plus or Team, the Agent is already starting to roll out. Just switch to "agent mode" in the tools menu or type "/agent" to try it. Enterprise and Education users will get it later this summer, while folks in Europe and Switzerland will need to wait a bit longer – OpenAI hasn't set a rollout date there yet. Why? Well, my guess is because of the stricter laws related to AI in those regions. Speaking of which, of course, with great power comes… yeah, you guessed it: concerns. But OpenAI claims it is putting new safety systems in place to prevent abuse. For one, there's a real-time monitor that checks interactions as they happen (not sure how great that is about privacy, though). It uses a built-in classifier to flag prompts tied to sensitive areas like chemical or biological weapons. And interestingly, memory is off by default – meaning the agent won't remember past convos to avoid the risk of prompt injection hacks. OpenAI says it might bring memory back later, but only if it's safe to do so. Now, is this the future? Probably yes. Still, we'll have to wait and see how all of this plays out in the real world. As cool as it sounds, it's one thing to promise a smart agent that can handle your digital life – it's another to actually make it reliable and secure enough to use daily. Personally, I'm not totally on board with this whole "let's put AI in every corner of our lives and see what happens" vibe. But the big tech players clearly are. Google, for example, If you're subscribed to ChatGPT Pro, Plus or Team, the Agent is already starting to roll out. Just switch to "agent mode" in the tools menu or type "/agent" to try it. Enterprise and Education users will get it later this summer, while folks in Europe and Switzerland will need to wait a bit longer – OpenAI hasn't set a rollout date there yet. Why? Well, my guess is because of the stricter laws related to AI in those of which, of course, with great power comes… yeah, you guessed it: concerns. But OpenAI claims it is putting new safety systems in place to prevent one, there's a real-time monitor that checks interactions as they happen (not sure how great that is about privacy, though). It uses a built-in classifier to flag prompts tied to sensitive areas like chemical or biological interestingly, memory is off by default – meaning the agent won't remember past convos to avoid the risk of prompt injection hacks. OpenAI says it might bring memory back later, but only if it's safe to do is this the future? Probably yes. Still, we'll have to wait and see how all of this plays out in the real world. As cool as it sounds, it's one thing to promise a smart agent that can handle your digital life – it's another to actually make it reliable and secure enough to use I'm not totally on board with this whole "let's put AI in every corner of our lives and see what happens" vibe. But the big tech players clearly for example, just announced its own batch of new AI agent features baked right into Search . One lets you ask AI to call stores and get prices and availability for things like dry cleaners or pet groomers – then it reports back with the results. So now you don't even have to make a phone call. Wild times, huh? OpenAI just dropped something big again – and this time, it's not a new model. While the company puts the brakes on its next-gen open-source model , it's hitting the gas with a brand-new feature for ChatGPT: a fully-fledged AI agent that can actually do things for you, not just OpenAI is officially joining the AI agent race. If you've been hearing all the buzz around these supercharged digital helpers that can handle multi-step tasks instead of just talking back to you – this is that. And OpenAI's version is called ChatGPT new tool isn't starting from scratch. The agent brings together the brains of OpenAI's other tools, like Operator – which can browse and click around websites – and Deep Research – which can pull info from all over the internet and turn it into neatly packaged reports. But now, instead of just getting answers, you can literally get stuff done – by simply typing out what you want in plain kind of stuff, you ask? OpenAI showed examples like checking your calendar to prepare you for client meetings, ordering ingredients for a big family breakfast or building a slide deck comparing your company to with ChatGPT Connectors, it can hook into Gmail, Google Drive, GitHub, and more – pulling in info that's actually useful based on what you are don't worry, it's not just going rogue (at least it's not supposed to). You're still the one in charge. ChatGPT asks for permission before it takes action and you can stop or jump in at any time if you want to take says this all makes ChatGPT way more useful – at work and at home. In your 9-to-5, you can use it to whip up presentations from dashboards, shuffle meetings around, update spreadsheets without messing up your formatting and even organize your next team offsite. And for your personal life? Plan a trip, book a dinner party, schedule a dentist appointment – all with one prompt.
Hans India
18-07-2025
- Business
- Hans India
OpenAI Rolls Out ChatGPT Agent: Sam Altman Says 'You Can Feel the AGI'
In a significant leap toward realizing artificial general intelligence (AGI), OpenAI has unveiled ChatGPT Agent, a groundbreaking tool that enables its AI to perform complex tasks autonomously using a virtual computer. OpenAI CEO Sam Altman marked the occasion with a bold statement on X: 'You can feel the AGI.' The ChatGPT Agent seamlessly merges conversational intelligence with task automation, web browsing, coding, and app integration, allowing users to offload real-world jobs—like scanning calendars, summarizing meetings, researching competitors, shopping online, or even submitting expenses—with minimal guidance. It works through a self-contained virtual machine, preserving context while switching fluidly between browsing and execution. This new feature is currently available for ChatGPT Pro, Plus, and Team users in the United States, with Enterprise and Education versions expected soon. Pro subscribers will receive 400 agent-mode messages per month, while others will have access to 40. For those needing more, a credit-based add-on system is available. Deep Research, one of the tools bundled into the agent's suite, will remain separately accessible for users preferring more detailed outputs. Unlike its predecessor, Operator—limited to website interaction—or the slower, analytical Deep Research mode, the ChatGPT Agent brings both capabilities together in one cohesive experience. It also integrates with apps like Gmail and GitHub, expanding the reach of what it can do. Whether it's planning a weekly report or crafting a project presentation, the agent uses a mix of tools—visual browser, terminal, text input, and more—to complete multi-step workflows. However, OpenAI emphasizes user control and safety. The AI won't take critical actions—like logging into accounts, sending emails, or making online purchases—without first seeking explicit approval. Users can pause, cancel, or step in during any task. There's also an option to schedule tasks to run regularly, such as generating weekly performance summaries. With this increased autonomy comes greater responsibility and risk. One major concern is prompt injection—where malicious instructions on a webpage could trick the AI into taking unintended actions. OpenAI says its system is trained to detect and avoid such threats, and actively monitors for anomalies during operation. Privacy is also a priority. According to OpenAI, ChatGPT Agent doesn't save login credentials. Users can delete browsing data or log out from all connected sites in a single step. Session data remains confidential, and cookie usage complies with individual site policies. While the feature is still maturing—especially in areas like slide deck creation, which remains in beta—OpenAI promises ongoing improvements to layout consistency and export quality. The company has yet to confirm when the feature might become available in India or other regions outside the U.S., although deployment in the European Economic Area and Switzerland is reportedly underway. OpenAI also announced that its earlier Operator preview will be phased out in the coming weeks, giving way to this more advanced and versatile agentic system.
NBC News
17-07-2025
- Business
- NBC News
OpenAI's ChatGPT 'agent' is ready to assist you
Looking for a wedding dress? Let AI order it for you. That's the promise of OpenAI's new "agent," which the company debuted in a livestream Thursday. 'Agent represents a new level of capability for AI systems and can accomplish some remarkable, complex tasks for you using its own computer,' OpenAI CEO and co-founder Sam Altman said in an X post. The announcement adds OpenAI to a growing list of tech companies seeking to move AI beyond text and image generation and into the realm of personal digital assistants. Other companies are pushing AI into web browsers with the promise of helping people complete tasks like making a restaurant reservation. In a livestream broadcast on its website, OpenAI executives gave a demonstration showing how its "ChatGPT agent" software could perform specific tasks, like ordering a dress that would be appropriate for a warm-weather destination wedding. It was also able to design laptop stickers featuring their team mascot and create a slide deck of ChatGPT agent's performance, pulling data from Google Drive. The debut comes as tech companies invest heavily in AI talent and infrastructure, with almost every major player having already made sizable investments. Earlier this week, Mark Zuckerberg, the CEO of Facebook parent Meta, announced his company would spend 'hundreds of billions of dollars' on artificial intelligence compute infrastructure. Meta also poached a senior Apple engineer with a pay package reportedly valued at some $200 million. OpenAI was most recently valued at $300 billion, making it one of the most valuable privately held startups in the world. The presentation revealed ChatGPT agent to be not entirely free from making errors. Altman cautioned in his X post that he would "explain this to my own family as cutting edge and experimental; a chance to try the future, but not something I'd yet use for high-stakes uses or with a lot of personal information until we have a chance to study and improve it in the wild." The technology prompts users for when logins or permissions are needed while giving human users the ability to intervene or take over at any point. For now, its access is limited to ChatGPT Pro, Plus, and Team users. In a followup X post, Altman indicated he believes that despite its current limits, the product represents a breakthrough. "Watching chatgpt agent use a computer to do complex tasks has been a real 'feel the agi' moment for me; something about seeing the computer think, plan, and execute hits different," he wrote, using the acronym for Artificial General Intelligence, seen as the holy grail of AI development.
