Latest news with #Operator
Business Insider
3 days ago
- Business
- Business Insider
I'm Expedia's marketing chief. Here's how we're preparing for a future when people use AI to plan their vacations.
This as-told-to essay is based on a conversation with Jochen Koedijk, Expedia Group's chief marketing officer. It's been edited for length and clarity. The way consumers are using the internet to make their decisions is fundamentally changing. I have two kids, 10 and seven years old, and I think it's very unlikely they will ever put a query into a search box, as I've grown up doing. The way people are using voice and having real conversations is going to be a long-term change in how people are using the internet. What we're seeing today is that a lot of the inspirational travel searches are evolving rapidly with things like Copilot, ChatGPT, and even Instagram Reels. There are a lot of moments where my wife sends me Reels, and she's like, "Where is this?" And I have no idea. So then, we were like, what if we can develop something where you send those Reels to Expedia, and then we will tell you: "It's this destination, or this hotel. Here are a couple of things to do. The best time to visit is between May and July, and here are a couple of booking options so you can get started." Right now, it's still early access, which means it's only with Reels, but we're looking at other forms of content as well. It's a very different journey versus going to and typing in "best hotels in Miami with pool, minus spa." We're also focusing on the visibility of our brands in agentic search engines. It's really evolving. We've launched with Operator for OpenAI, which I still see as a precursor to an agentic interface because you're looking at the cursor moving on your screen. Of course, true agentic, where it's going, will be more behind-the-scenes. But it's very important to be early so that we can experiment and iterate. Another example is being a launch partner for Copilot Plus, which is the way Microsoft is evolving. There's so much development between each of these LLM providers and depending on which week of the month, there's a new model here, and things completely change. There are a lot of AI experts popping up left, right, and center. It's important for us to make sure that we do a lot of our marketing in-house — the majority — and that we further evolve our in-house functions to be ready for the future. Google is a very important partner of ours. A lot of our traffic is still from Google. The way they're using Gemini with AI Overviews is already impacting our existing traffic in a big way. We look to understand which search queries are triggering AI overviews, and then we look at our traffic trends, and we triangulate. So we could, for example, see that certain keyword buckets trigger more overviews than last month, and that will have a certain impact on traffic and conversion. Traffic may go down, but conversions may go up because the traffic becomes more qualified. I do believe the funnel — as we call it as marketers — will start to collapse more and more over time. We want to make it a lot more seamless so that there is not that kind of disconnect between the inspiration and the action.
Forbes
5 days ago
- Business
- Forbes
The Power And The Promise Of ChatGPT Operator
To somewhat limited fanfare, OpenAI has come out with a groundbreaking tool that can use a computer for you, and it's been out most of this year, available to the company's elite tier of 'pro' users. Operator is powered by something called a computer using agent or CUA that allows the model to 'see' content on the Internet, and take actions that a human would take with a mouse and a keyboard. That means the Operator can accomplish the full life cycle of a task, such as booking a reservation or signing someone up for something. I thought it was time to address the remaining barriers to massive adoption of this agentic AI tool, as spring winds into summer. The first problem is cost. Operator now costs $200 a month, compared to $20 a month for all of the other things that ChatGPT can do. It seems like the vast majority of average users are waiting for the cost to come down. Read this review from Mike Todasco at Medium, and you'll see that he just doesn't feel like the technology is worth $200 a month: 'If this is the future, then I don't think we need to worry about AI Agents taking our jobs,' Todasco writes. 'Operator is a mess, and sure as heck not worth an extra $180/month. I spent several days trying to find any usefulness in it. But in the end, I had to hang up on this experiment.' What if it was $40 a month? Where would daily user numbers be at right now? Of course, we don't really have anything to compare it to, since OpenAI has not released user numbers for Operator currently. You could also make the argument that Operator is vaguely genetic – that although it has the ability to use the Internet, it doesn't have prebuilt task management tools in hand. It's more of a do-it-yourself kind of task-based system. The CUA is absolutely compelling as technology – it combines prior work on computer vision and tool use to offer the kind of environment that we've been waiting for a long time. However, for most people, it's still too expensive. Right now, people are adding their own data to ChatGPT in granular ways, to come up with responses. The same would apply to task-based systems. You're going to have to decide how much data you trust Operator with in order for it to do its work. You'll have to also figure out how much you want to delegate, and what you want to keep for yourself. And we'll have to figure out, as users, how to deal with the hacker community, where black hats and bad actors will presumably be trying to get Operator to do things that you don't want it to do. However, there's so much potential here that I thought it warranted a post today to talk about the potential moving forward, and that makes sense, since the company just recently unveiled Operator o3. Cark Franzen at VentureBeat provides these potential use cases: 'Data engineers can delegate manual web interactions—such as data verification and scraping—with more confidence, freeing time for higher-level optimization work. Security professionals, meanwhile, gain a safer way to simulate user behavior in audits and incident response exercises, thanks to the model's layered safety mechanisms.' Over at Reddit, OpenAI did an AMA (Ask Me Anything) on Operator, where VP of Research Jerry Tworek said this: "We… already have a product surface that can do things on your computer … we're planning to make some improvements soon and it can become a very useful tool then.' If you agree with this assessment, we are very close to enormous user bases playing around with the first over-the-counter agentic systems of their kind. We just need a little bit of a discount.
Yahoo
6 days ago
- Entertainment
- Yahoo
A.J. Croce to play ARIA Ballroom at MGM Springfield this fall
SPRINGFIELD, Mass. (WWLP) – At MGM Springfield, Americana singer A.J. Croce will be performing in the Aria Ballroom this fall. Train to perform at The Big E Arena in September The performance is on November 21 at 8:00 p.m. Tickets go on sale Friday at 10:00 a.m., and MGM rewards members can be among the first to secure tickets with pre-sale access starting on Thursday. The musician will be performing 'Croce Plays Croce,' a special night of music featuring a complete set of classics by his late father, Jim Croce, including hits such as 'Operator,' 'Time in a Bottle,' and 'Bad, Bad Leroy Brown.' A.J. Croce has performed for 30 years, touring with well-known artists like Willie Nelson, Lenny Kravitz, and Earth, Wind, and Fire. For more information on this concert and other upcoming events, visit WWLP-22News, an NBC affiliate, began broadcasting in March 1953 to provide local news, network, syndicated, and local programming to western Massachusetts. Watch the 22News Digital Edition weekdays at 4 p.m. on Copyright 2025 Nexstar Media, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.
Business Mayor
24-05-2025
- Business
- Business Mayor
OpenAI updates Operator to o3, making its $200 monthly ChatGPT Pro subscription more enticing
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More It was a big week for AI announcements following events from Microsoft, Google, and Anthropic. But OpenAI is finishing things out with news of its own. And no, we're not just talking about its $6.5 billion acquisition of Jony Ive's design team to lead a new hardware effort, 'io' at OpenAI. Today, the company upgraded its Operator autonomous web browsing and cursor controlling agent within ChatGPT from using the prior GPT-4o multimodal large language model to the newer and more powerful o3 reasoning model. The update, released globally today, May 23, 2025, is available as a 'research preview' to paying subscribers of OpenAI's $200 USD-monthly ChatGPT Pro plan. Basically, that is OpenAI's way of saying it's not a fully 'sanded down' or perfected product yet — it may still have kinks and issues. But with rival Google offering its own top tier AI subscription bundle for a price of nearly $250 USD regularly (currently running a discount down to $125 for the first three months) to access its latest Gemini multimodal, Imagen image generation, and Veo video generation models, suddenly OpenAI's ChatGPT Pro plan seems more affordable by comparison. Operator first debuted in January 2025 as OpenAI's initial step into semi-autonomous agents, specifically Computer Using Agents (CUAs). The idea is to go beyond the chatbot interface of ChatGPT and allow OpenAI's powerful AI models to start taking more actions on behalf of the user. Thus, Operator was designed to autonomously point, click, scroll, and type to complete web-based tasks such as booking dinner reservations, compiling shopping lists, or ordering event tickets. This agentic capability allows it to complete user tasks directly through a browser interface, from booking reservations to gathering online data. Read More Daedalic closes game development after Gollum flop For safety, privacy and security purposes, Operator didn't use any existing web browser on a user's PC or Mac. Instead, it ran in a cloud-hosted virtual browser accessible via a standalone site— users could input requests and observe the agent perform tasks in real time. It combined vision, reasoning, and interaction capabilities based on GPT-4o, marking a new direction for OpenAI in agentic AI. The product was launched as a research preview for ChatGPT Pro subscribers and featured built-in safety measures like user confirmations, Watch Mode, and restrictions on high-risk web platforms. It was also being tested in enterprise contexts, including travel planning and civic services, demonstrating its potential across both consumer and business environments. With this update, OpenAI aims to enhance performance across several key dimensions. The new o3-based Operator demonstrates improved persistence and accuracy during browser interactions. In practical terms, this means it is more likely to complete user tasks successfully and with less need for correction or repetition. Moreover, users can expect responses that are clearer, more structured, and more comprehensive. In comparative evaluations, the new model shows a distinct preference advantage over its predecessor. Human preference studies reveal that users favor the o3 model for its style, comprehensiveness, and clarity. It also performs strongly in instruction following and efficiency, though results for factual correctness are more balanced between versions. Performance on third-party evaluation benchmarks reflects these enhancements. On the OSWorld benchmark that measures completion of browser-based tasks, the o3 model scores 42.9 compared to 38.1 for the previous version. However, OpenAI notes that due to limitations in the automated grading system, the actual performance gain could be closer to 20 percentage points! On WebArena, the new model achieved a score of 62.9, up from 48.1. The most dramatic improvement appears on the GAIA benchmark, where the o3 model scores 62.2, vastly surpassing the prior model's 12.3. Side-by-side task comparisons further illustrate these gains. In one example involving a restaurant booking request, the new model provided a clearer and more detailed list of available reservations, including locations, Michelin ratings, and seating notes, presented in a well-formatted table. The previous version, while functional, delivered less information in a less organized manner, according to an image included with the new o3 Operator release notes: Safeguards remain, as do general cautionary notes about usage on sensitive, financial transactions and account access The o3 model also inherits the safety measures introduced with earlier versions, with further fine-tuning for its role as an agentic system. OpenAI has integrated enhanced training against harmful task execution, prompt injection vulnerabilities, and mistakes involving user intent. Evaluations show that the model now confirms 94% of sensitive actions before executing them, with 100% confirmation in financial transactions. Prompt injection susceptibility has also decreased from 23% to 20%. Notably, the o3 Operator maintains a cautious boundary on certain high-risk web interactions, such as email or financial platforms, where it may require user supervision via Watch Mode or explicitly refuse to proceed. These measures are part of a layered approach to safety that combines model-level robustness with real-time monitoring. While the upgrade to Operator marks a technical improvement, it also reflects OpenAI's ongoing commitment to responsible AI deployment. The system's ability to take real-world actions introduces new risks, and the development team continues to refine its safety protocols accordingly. Read More Approaching the issue of diversity in the tech industry According to OpenAI's updated o3 system card documentation, the model remains below high-risk capability thresholds in categories such as biological and chemical misuse and has no native coding environment or terminal access, further reducing potential misuse vectors. Operator remains a research preview and is accessible only to ChatGPT Pro users. The Responses API version of Operator will continue to be based on the GPT-4o model, at least for now. The upgraded Operator stands to significantly enhance the workflows of professionals in AI engineering, orchestration, data management, and IT security. For those building or maintaining machine learning models, the model's improved accuracy and structured outputs reduce the overhead of test validation and troubleshooting. In orchestration contexts, it offers a practical, reliable tool for automating browser-based components of complex pipelines. Data engineers can delegate manual web interactions—such as data verification and scraping—with more confidence, freeing time for higher-level optimization work. Security professionals, meanwhile, gain a safer way to simulate user behavior in audits and incident response exercises, thanks to the model's layered safety mechanisms. Across these disciplines, the o3-based Operator introduces both a capability upgrade and a risk mitigation framework, making it a practical addition to the modern technical toolkit.
Economic Times
24-05-2025
- Economic Times
OpenAI upgrades Operator with o3 model for enhanced reasoning, safety
OpenAI is updating the artificial intelligence (AI) model powering Operator, its AI agent that can autonomously browse the web and interact with certain software inside a cloud-hosted virtual machine to carry out user requests. Operator will soon run on a model based on o3, one of the latest in OpenAI's o series of 'reasoning' models. Previously, Operator relied on a customised version of GPT-4o. By several benchmarks, o3 is a more advanced model, particularly on tasks requiring mathematical ability and reasoning. 'We are replacing the existing GPT‑4o-based model for Operator with a version based on OpenAI o3,' OpenAI wrote in a blog post. 'The API version (of Operator) will remain based on 4o.' Operator is part of a growing set of agentic tools developed by AI firms as they compete to build agents capable of reliably performing digital tasks with minimal supervision. Google offers a similar agent through its Gemini API, which can browse the web and take actions on users' behalf. It also offers a consumer-facing version called Mariner. Anthropic's models can perform various computer tasks as well, including opening files and navigating webpages. According to OpenAI, the upgraded Operator model, dubbed o3 Operator, was 'fine-tuned with additional safety data for computer use,' using datasets designed to 'teach the model (OpenAI's) decision boundaries on confirmations and refusals.'The company has released a technical report detailing o3 Operator's performance in safety evaluations. Compared to the GPT-4o version, the new model is less likely to carry out illicit activities, search for sensitive personal data or fall prey to prompt injection, a common AI attack technique.'o3 Operator uses the same multi-layered approach to safety that we used for the 4o version of Operator,' OpenAI wrote in its blog post. 'Although o3 Operator inherits o3's coding capabilities, it does not have native access to a coding environment or terminal.'
