Latest news with #DeepResearch
Yahoo
3 days ago
- Business
- Yahoo
Jefferies Names Microsoft (MSFT) Its Top AI Pick After 'Build 2025'
Jefferies' top tech analyst, Brent Thill, has named Microsoft Corp. (NASDAQ: MSFT) his 'top AI pick' following the company's annual developer conference, Build 2025, held in Seattle last week. In a research note on May 23, Thill reaffirmed his Buy rating on the stock and maintained a price target of $550, highlighting Microsoft's strategic focus on artificial intelligence as a key driver of future growth. Asif Islam / Thill described Microsoft Corp. (NASDAQ: MSFT) evolving into a comprehensive AI platform, positioning it to lead in the fast-moving AI landscape. He emphasized the company's growing momentum in AI services and infrastructure, noting a strong reception from the developer community. One of the standout themes from Build 2025 was Copilot, Microsoft's AI assistant, which Thill said had made meaningful progress over the past three to six months. Developers were particularly enthusiastic about its enhanced capabilities and the ease with which it can integrate next-generation reasoning models. Thill also noted that the updated Copilot now features advanced research tools, which he believes will help close the functionality gap with OpenAI's Deep Research, further strengthening Microsoft's competitive edge in enterprise AI solutions. With continued innovation and broad developer support, Microsoft remains a major force in shaping the future of artificial intelligence, according to Jefferies. While we acknowledge the potential of MSFT as an investment, our conviction lies in the belief that some AI stocks hold greater promise for delivering higher returns and have limited downside risk. If you are looking for an AI stock that is more promising than MSFT and that has 100x upside potential, check out our report about this . Read More: and Disclosure: None. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Yahoo
22-05-2025
- Business
- Yahoo
Skywork.ai Launches Globally, Introducing the World's First DeepResearch-Powered Workspace Super Agents
Singapore , May 22, 2025 (GLOBE NEWSWIRE) -- In May 2025, officially entered the global stage, launching the world's first AI Office Suite powered by DeepResearch technology, with full support for both English and Japanese to enhance productivity across language barriers. While most AI tools remain limited by shallow retrieval and generic output, introduces a new standard—combining enterprise-grade automation with deep, verifiable research across documents, spreadsheets, and presentations. At the heart of this launch is Docs, Sheets, and Slides trio, the first in the world to apply DeepResearch not just to written reports, but also to data analysis and presentation generation. Unlike platforms that rely on narrow RAG-based methods, performs 10x deeper content searches, enabling richer insights, more accurate results, and intelligent visualizations—including tables, charts, and graphs—tailored to professional conventional AI tools that aim for broad capability but lack functional depth, introduces a vertically specialized system of five expert agents—focused respectively on professional documents, data sheets, presentations, podcasts, and web content. Each agent is designed to deliver high-quality, context-aware results tailored to real-world use cases. By aligning advanced AI capabilities with the practical demands of work and study, enables users across industries to produce credible, editable, and ready-to-use content—transforming the role of AI from assistant to true productivity AI for Real-World Productivity offers five expert agents—each dedicated to a key task: writing documents, analyzing spreadsheets, building presentations, producing podcasts, and creating websites. This structure solves a core industry problem: generic AI tools are broad but shallow. prioritizes task-specific depth, delivering outputs that are accurate, editable, and ready for immediate use. Backed by a proprietary multimodal model and a modular plug-in ecosystem, the platform supports seamless cross-format content generation, from business reports and data visualizations to podcasts and promotional videos. What Enables for You Purpose-Built for Professional Workflows Workspace Suite—Docs, Sheets, and Slides—is purpose-built for high-stakes professional use, anchored by one of the industry's most powerful research engines: DeepResearch, which makes it the first and only platform globally to offer Slides and Sheets that are grounded in comprehensive, high-fidelity research. With up to 10 times the search depth of comparable platforms, captures a far broader and richer spectrum of information—allowing users to generate content that rivals expert-level research, consulting-grade insights, and academic rigor. This isn't just about volume—it's about intelligence at scale. enhanced research depth enables: Comprehensive coverage of relevant materials, reducing blind spots in analysis. Cross-source validation, minimizing AI hallucinations and ensuring factual consistency. Domain-aware synthesis, producing content that understands nuance, context, and industry logic. Docs generates structured, source-backed reports and professional writing; Sheets turns raw data into clear, visualized analysis; Slides creates polished, editable presentations with varied formats and logical flow. This DeepResearch capability ensures every piece of content produced by is professionally polished and grounded in reliable sources—enabling teams, consultants, and researchers to move faster without compromising Tasks Start with Smarter Inputs empowers users to get better results by first helping them define better tasks. Through its intelligent prompt clarification system, the platform doesn't just respond—it listens. Instead of acting on vague instructions, automatically generates a personalized input form tailored to the task, prompting users to clarify goals, context, and constraints. This ensures the AI understands what's actually needed before generating output. This means less time rewriting or correcting, and more time acting on high-quality results that align with their real-world objectives—whether it's drafting a report, building a presentation, or analyzing data. Traceable Sources and Transparent Logic sets a new benchmark for content transparency with its advanced source-tracing system. Unlike other tools that merely attach raw URLs, goes further—identifying the exact passage within the source and displaying it in a real-time pop-up. This allows users to see not just where the information came from, but exactly what was referenced, all without leaving the platform. This level of transparency is critical for professionals who need to defend their work, researchers who require accuracy, and students who must cite reliable references. With users can move from creation to delivery without second-guessing the validity of their content—enabling faster decisions, stronger arguments, and results they can stand behind. Editable, Exportable, and Built for Real-World Use is the first platform to integrate DeepResearch with advanced, dynamic data visualization—enabling users to generate professional-grade reports that are not only rich in insight, but also visually compelling. automatically generates tailored visual elements based on user intent. From tables and bar charts to pie charts, line graphs, scatter plots, and radar charts, users can specify what they need—and Skywork delivers, all within the same workflow. All outputs are fully editable, version-tracked, and exportable in formats like PDF, PPTX, and HTML—making them ready for real-world use without leaving the Value, Lower Cost offers unmatched value with general tasks priced only 70% of the industry average. This allows users to access powerful, professional-grade AI tools at minimal cost, making it easy to scale content creation without sacrificing quality or budget. Beyond Text: Multimodal Creation that Stands Out empowers users to create multimedia content—videos, voiceovers, music, and images—within one platform. From MVs to audiobooks and visual stories, users can produce polished, engaging outputs without extra tools or technical skills. Your Content, Smarter Over Time enables users to create a private, persistent knowledge base by uploading documents, links, and media assets, which extends further by supporting multi-modal content generation—including reports, presentations, spreadsheets, web pages, and podcasts—all grounded in the user's own source material. This enables quick content generation from existing materials and easy reuse of past work—streamlining research, saving time, and creating a smarter, evolving workspace. Redefining Productivity for the AI Era More than a tool, is a platform purpose-built to elevate professional output. It leverages advanced AI capabilities to deliver expert-level content creation, tailored to real-world use cases across industries. With a scalable architecture, enterprise-grade reliability, and a focus on trust and performance, stands at the forefront of next-generation productivity solutions. Now Available –19.99USD offers exceptional value for individuals and organizations seeking to integrate intelligent automation into their operations. Designed for immediate impact, it enables faster, smarter, and more consistent results—at a fraction of the time and cost. Unlock the Future of Work Today Harness the full power of AI and operate with the agility of a team—no matter the size of the workforce. Discover more and get started at: Stay connected for updates and insights: X (Twitter): YouTube: Github： Jane Wang skywork jane at in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Hindustan Times
22-05-2025
- Hindustan Times
Dyson launches ‘world's slimmest' vacuum cleaner PencilVac: What you need to know
What if we tell you that you can get a vacuum cleaner as thin as a broom? Well, Dyson, the premium home appliance brand, has announced the global launch of the world's slimmest vacuum cleaner, the PencilVac. As the name suggests, the vacuum cleaner has a slim body, features Dyson's smallest vacuum motor, and measures just 38mm in diameter to clean the narrowest corners of the home. Alongside the slimness and lightweight design, the company claims that the cleaner comes with advanced technology and features, offering powerful performance. Therefore, if you are planning a hassle-free vacuum cleaner for your home, then you may want to consider buying the new Dyson PencilVac. Know about its features and the technology used to get a better understanding of what it has to offer. Also read: Paytm introduces option to hide specific transactions from history: Here's how it works With the Dyson PencilVac, the company introduces new Dyson Fluffycones in two brush bars as the cleaner head. These concial bars move in different directions for advanced cleansing. For instance, two sets of cones spin in the forward direction, and the other spins backwards. This helps to automatically push hair off the brush, and it does not get tangled on the brush. The cleaner is powered by the new Dyson Hyperdymium 140k motor, which the company claims to be the 'fastest vacuum motor to date.' The claims that this new motor offers greater power density and is 34% more efficient than its predecessor. It claims to offer up to 140,000 RPM rotational speed and generate 55AW of suction. Also read: ChatGPT now lets you download Deep Research reports as PDFs - here's how The Dyson PencilVac features a new filtration system that separates dust and debris using airflow. Dyson said it 'effectively separates dust and debris from the airflow without causing filters to clog or cleaning performance to decline.' Its two-stage linear dust separation system captures 99.99% of particles as small as 0.3 microns. The vacuum cleaner also features an air-compressing bin and a hygienic syringe bin ejection system. It should be noted that the Dyson PencilVac is a cordless vacuum, offering greater convenience while cleaning spaces. The cleaner can be connected via the MyDyson, from where users can manage additional settings. The Dyson PencilVac is launched in the global market as of now. The cleaner is expected to launch in India as well. Therefore, we may have to wait a little longer to confirm the India pricing for the new slimmest vacuum cleaner. Mobile Finder: Samsung Galaxy S25 Ultra LATEST specs, features, and price
Business Mayor
21-05-2025
- Business
- Business Mayor
OpenAI updates its new Responses API rapidly with MCP support, GPT-4o native image gen, and more enterprise features
Join our daily and weekly newsletters for the latest updates and exclusive content on industry-leading AI coverage. Learn More OpenAI is rolling out a set of significant updates to its newish Responses API, aiming to make it easier for developers and enterprises to build intelligent, action-oriented agentic applications. These enhancements include support for remote Model Context Protocol (MCP) servers, integration of image generation and Code Interpreter tools, and upgrades to file search capabilities—all available as of today, May 21. First launched in March 2025, the Responses API serves as OpenAI's toolbox for third-party developers to build agentic applications atop some of the core functionalities of its hit services ChatGPT and its first-party AI agents Deep Research and Operator. In the months since its debut, it has processed trillions of tokens and supported a broad range of use cases, from market research and education to software development and financial analysis. Popular applications built with the API include Zencoder's coding agent, Revi's market intelligence assistant, and MagicSchool's educational platform. The Responses API debuted alongside OpenAI's open-source Agents SDK in March 2025, as part of an initiative to provide third-party developer access to the same technologies powering OpenAI's own AI agents like Deep Research and Operator. This way, startups and companies outside of OpenAI could integrate the same tech as it offers through ChatGPT into their own products and services, be they internal for employee usage or external for customers and partners. Initially, the API combined elements from Chat Completions and the Assistants API—delivering built-in tools for web and file search, as well as computer use—enabling developers to build autonomous workflows without complex orchestration logic. OpenAI said at that time that the Chat Completions API would be deprecated by mid 2026. The Responses API provides visibility into model decisions, access to real-time data, and integration capabilities that allowed agents to retrieve, reason over, and act on information. This launch marked a shift toward giving developers a unified toolkit for creating production-ready, domain-specific AI agents with minimal friction. A key addition in this update is support for remote MCP servers. Developers can now connect OpenAI's models to external tools and services such as Stripe, Shopify, and Twilio using only a few lines of code. This capability enables the creation of agents that can take actions and interact with systems users already depend on. To support this evolving ecosystem, OpenAI has joined the MCP steering committee. The update brings new built-in tools to the Responses API that enhance what agents can do within a single API call. A variant of OpenAI's hit GPT-4o native image generation model — which inspired a wave of 'Studio Ghibli' style anime memes around the web and buckled OpenAI's servers with its popularity, but can obviously create many other image styles — is now available through the API under the model name 'gpt-image-1.' It includes potentially helpful and fairly impressive new features like real-time streaming previews and multi-turn refinement. This enables developers to build applications that can produce and edit images dynamically in response to user input. Additionally, the Code Interpreter tool is now integrated into the Responses API, allowing models to handle data analysis, complex math, and logic-based tasks within their reasoning processes. The tool helps improve model performance across various technical benchmarks and allows for more sophisticated agent behavior. Improved file search and context handling The file search functionality has also been upgraded. Developers can now perform searches across multiple vector stores and apply attribute-based filtering to retrieve only the most relevant content. This improves the precision of information agents use, enhancing their ability to answer complex questions and operate within large knowledge domains. Several features are designed specifically to meet enterprise needs. Background mode allows for long-running asynchronous tasks, addressing issues of timeouts or network interruptions during intensive reasoning. Reasoning summaries, a new addition, offer natural-language explanations of the model's internal thought process, helping with debugging and transparency. Encrypted reasoning items provide an additional privacy layer for Zero Data Retention customers. These allow models to reuse previous reasoning steps without storing any data on OpenAI servers, improving both security and efficiency. The latest capabilities are supported across OpenAI's GPT-4o series, GPT-4.1 series, and the o-series models, including o3 and o4-mini. These models now maintain reasoning state across multiple tool calls and requests, which leads to more accurate responses at lower cost and latency. Despite the expanded feature set, OpenAI has confirmed that pricing for the new tools and capabilities within the Responses API will remain consistent with existing rates. For example, the Code Interpreter tool is priced at $0.03 per session, and file search usage is billed at $2.50 per 1,000 calls, with storage costs of $0.10 per GB per day after the first free gigabyte. Web search pricing varies based on the model and search context size, ranging from $25 to $50 per 1,000 calls. Image generation through the gpt-image-1 tool is also charged according to resolution and quality tier, starting at $0.011 per image. All tool usage is billed at the chosen model's per-token rates, with no additional markup for the newly added capabilities. With these updates, OpenAI continues to expand what is possible with the Responses API. Developers gain access to a richer set of tools and enterprise-ready features, while enterprises can now build more integrated, capable, and secure AI-driven applications. All features are live as of May 21, with pricing and implementation details available through OpenAI's documentation.
Yahoo
21-05-2025
- Business
- Yahoo
Google updates the Gemini app with real-time AI video, Deep Research, and more
Google announced several updates to the Gemini AI chatbot app during Google I/O 2025, including more broadly available multimodal AI features, updated AI models, and deeper integrations with Google's suite of products. Starting Tuesday, Google is rolling out Gemini Live's camera and screen-sharing capabilities to all users on iOS and Android. The feature, powered by Project Astra, allows users to have near-real-time verbal conversations with Gemini, while simultaneously streaming video from their smartphone's camera or screen to the AI model. For example, while walking around a new city, users could point their phone at a building and ask Gemini Live about the architecture or history behind it, and get answers with little to no delay. In the coming weeks, Google says Gemini Live will also start to integrate more deeply with its other apps. The company says Gemini Live will soon be able to offer directions from Google Maps, create events in Google Calendar, and make to-do lists with Google Tasks. The slew of updates to Google's Gemini are part of the company's efforts to compete with OpenAI's ChatGPT, Apple's Siri, and other digital assistant providers. The rise of AI chatbots has given users a new way to interact with the internet and their devices. This has put pressure on several Big Tech businesses, including Google Search and Google Assistant. Google announced during I/O 2025 that Gemini now has 400 million monthly active users, and the company surely hopes to grow that user base with these updates. Google introduced two new AI subscriptions: Google AI Pro, a rebrand for its $20-per-month Gemini Advanced plan, and Google AI Ultra, a $250-per-month plan that competes with ChatGPT Pro. The Ultra plan gives users very high rate limits, early access to new AI models, and exclusive access to certain features. U.S. subscribers to Pro and Ultra who have English selected as their language in Chrome will also get access to Gemini in their Chrome browser, Google announced Tuesday. The integration aims to let users ask Gemini to summarize information or answer questions about what appears on their screen. Google says it's updating Deep Research, Gemini's AI agent that generates thorough research reports, by allowing users to upload their own private PDFs and images. Deep Research will cross-reference these private PDFs with public data to create more personalized reports. The company says that soon users will be able to directly integrate Drive and Gmail to Deep Research. Free users of Gemini are getting an updated AI image model, Imagen 4, which Google says delivers better text outputs. Subscribers to the company's new $250-per-month AI Ultra plan will also get access to Google's latest AI video model, Veo 3, which generates sound that corresponds to video scenes through native audio generation. Google is also updating the default model in Gemini to be Gemini 2.5 Flash, which the company says will offer higher quality responses with lower latency. To cater to the growing number of students that use AI chatbots, Google says Gemini will now create personalized quizzes focused on areas that users find challenging. When users answer questions wrong, Gemini will help create additional quizzes and action plans to strengthen those areas. This article originally appeared on TechCrunch at
