Microsoft also announced that it’s moving from text-only search & chat to one that’s more visual with rich image/video answers and new multimodal support coming shortly. Users can get more visual answers including charts and graphs and updated formatting of answers, to help them find information more easily. Image Creator has also been expanded to all languages in Bing.

Microsoft Edge will be redesigned with a sleeker and enhanced UI and is adding the ability to incorporate visual search in chat so that users can upload images and search the web for related content.

Chat history allows users to pick up where they left off and return to previous chats in Bing chat with chat history. Chats can then be moved to Edge Sidebar so that they can be kept on hand while browsing. 

Microsoft stated that it will soon add export and share functionalities into chat for times when people want to easily share conversations with others on social media.

“The new AI-powered Bing has already helped people more easily find or create what they are looking for, making chat a great tool for both understanding and taking action. The integration of Image Creator saves you time by completing the task of creating the image you need right within chat,”  Yusuf Mehdi, corporate vice president and consumer chief marketing officer wrote in a blog post that contains additional details on the new features. 

The post Microsoft Bing AI moves to Open Preview, eliminating waitlist appeared first on SD Times.

This version also brings multiple other enhancements, including improvements to the way that Upgrade Assistant updates NuGet packages, upgraded Incremental scenario to use YARP 2.0, and improved error handling that shows all failures and warnings in the Progress View for each project component. 

According to Microsoft, in the last version of Upgrade Assistant, when the user chose to upgrade from .NET Core or later to .NET 6, 7, or 8, only the target framework was upgraded. With this release, however, all packages the application is referencing will be upgraded to a set of packages that correspond to the target .NET.

Users can also upgrade existing Xamarin.Forms applications to .NET MAUI, Xamarin’s successor, offering several new benefits and improvements such as single project to simplify asset management; NuGet management; and leverage multi-targeting.

Additionally, this upgrade brings multi-window support for desktop and table scenarios, a rebuilt layout geared at improving maintainability and performance, App Builder to standardize app bootstrapping with common .NET pattern, and a decoupled platform from  cross-platform controls.

There have also been upgrades made to Azure Functions. The company stated that when Azure Functions are upgraded to the latest .NET, the tool will also upgrade the user’s version of Azure Functions to the latest version (v4). The body of functions has also been updated to use the new APIs.

To learn more, read the blog post. 

The post Microsoft’s .NET Upgrade Assistant now offers support for .NET MAUI and Azure functions appeared first on SD Times.

Now, Microsoft is making it easier for companies to do so with the release of Semantic Kernel’s Copilot Chat sample app. Developers can use the new tool to integrate large language models (LLMs) into their applications. 

RELATED CONTENT: SD Times Open-Source Project of the Week: Semantic Kernel

The sample app enables multiple conversation topics, speech recognition, file uploads, persistent memory storage, and downloadable bots that can be shared with others. 

According to Microsoft, some ideas for apps that can be created are a customer service tool, personalized recommendation system, HR assistant, educational tool, or e-commerce assistant. 

Benefits include improved user experience because information is more easily obtained, improved efficiency by removing the need for human intervention, improved accessibility by providing personalized assistance to users based on their needs, and the ability to easily scale to meet demand. 

“By providing personalized assistance and natural language processing, your own chatbot can improve the user experience for customers, students, and employees alike. Users can get the information they need quickly and easily, without having to navigate complex websites or wait for assistance from a customer service representative,” Shannon Monroe, principal program manager at Microsoft, wrote in a blog post. 

Like the Semantic Kernel that it is built upon, Copilot Chat is open-source and can be accessed through GitHub.  

The post Microsoft’s new open-source project makes it easy to build generative AI into your applications appeared first on SD Times.

In CMake projects, users can simply click the “Run CTest” icon along the bottom status bar or the “Testing” side panel icon to launch the test explorer.

When the project is configured, the tests in your CMakeLists.txt will load in the Test Explorer.

The new feature allows users to view their tests’ detailed status and results, run specific tests or sets of tests, debug tests, and view test output. The tool also includes a refresh button for updating test information.

This release also features open-source community contributions from users.

Microsoft stated that it plans to experiment with the CMake tools’ user experience settings and implement CMake language services and a CMake Debugger in the future. 

Additional details are available here. 

The post CMake Tools 1.14 in VS Code adds Test Explorer for CTest appeared first on SD Times.

Generative AI is a new way for people to interface with their technology, but it has some shortcomings. 

Let’s talk about this from a developer’s standpoint, and about why, once generative AI becomes commonplace, we’ll likely have a very different group of companies like we did with the introduction of the Web.

Generative AI’s promise

The promise for generative AI is that you can use your natural, spoken language to ask the computer to do something and the computer will automatically do it. In Microsoft Office, the initial implementation is very sub-product-centric. For instance, you can request Word to create a document to your specifications, but you’ll have to go to PowerPoint or Excel if you want the tool to create a blended document. I expect the next generation of this Microsoft offering will bridge those apps and other products to allow you to create more complex documents just by putting in information the AI asks for to strengthen the piece. 

This is going to make for a difficult evolution for firms that have apps that don’t currently integrate well because the user will want one interface, not multiple AIs that each require different command language or that use different language models. 

The generative AI problem

While developing your own generative AI may help, long-term integration with the platform’s generative AI will quickly be a differentiator focused on user satisfaction and retention. I point out that last because users who get frustrated working with multiple generative AI platforms will likely begin preferring products that interoperate and integrate with a major generative AI solution so that the user doesn’t have to train and learn multiple generative AI offerings.

In short, one of the bigger problems is integrating the app with the generative AI most likely to be found on it. Neither Apple nor Google have a cooked generative AI model, and neither company is as good as Microsoft in terms of bringing partners on board to better address their lack of a generative AI solution. 

Assuring quality

The other big trend in generative AI is putting the technology into development tools that will allow the AI to become a coding accelerator. But with code, errors tend to proliferate. While this initial instance of generative AI is very fast, it’s anything but infallible. If you don’t want a lot of mistakes, the initial focus of any generative AI user needs to be on quality over quantity. The error-checking capability of generative AI is still very young and often makes mistakes. That means coders who use generative AI need to focus more on quality than they currently do. You’ll be training the tool while you use it, and if you train it to make a mistake, that mistake has the potential to proliferate and create additional problems. So, when using development tools that make use of generative AI, the massive increase in speed needs to be tempered with an increased focus on quality. Otherwise, your quality is likely to degrade badly over time.

Wrapping up

Generative AI is a game changer. It allows people to increasingly interact with their smartphones, PCs, apps and cloud services as if they were people. To make this work optimal, applications will need to be able to integrate under a generative AI umbrella so that the user only needs to make a request and the relevant app(s) is launched to complete the request. With its announcements of generative AI for its developer tools and Office, Microsoft is arguably the farthest along this path, but we are still early days, and this leadership is likely to become dynamic in the future.

The path to success will be to adapt an existing generative AI tool tactically but work to create the hooks to better integrate your app with the platform’s most likely generative AI solution so that you can dictate once and the AI will move between tools to complete the task. We’re far from that point now, but that gives you time to figure out how to address it.

In short, we are at the front end of a massive generative AI change. Make your related decisions very carefully because you want to be standing when this AI trend reaches critical mass and users move from products that haven’t embraced it much like they did with GUIs and the Web. 

The post Getting ready for the generative AI wave appeared first on SD Times.

The user experience has been improved so that it is easier to locate everything in one place. The company stated that these enhancements also work to build the foundation for Microsoft’s AI-powered experiences, such as Copilot for Microsoft Teams.

In an effort to bring users heightened speed, Microsoft has made a ground-up investment to overhaul the platform to provide speed and performance improvements for data, network, chat, and video architecture.

Enhancements have also been made to the core experience of Teams that are geared at simplifying the way customers stay on top of notifications, search for information, manage messages, and organize channels. 

Furthermore, Microsoft has improved the Teams authentication model, synchronization, and notification system to offer users a more consistent experience. 

According to the company, it will also use AI to improve collaboration by providing users with the information needed so they can be up to speed on everything that happened prior to joining a meeting or chat. Additionally, the next-gen AI experiences provide users with answers to questions in the flow of discussion.

To learn more about the new Teams, read the blog post. 

The post Microsoft Teams has been redesigned to offer increased speed appeared first on SD Times.

According to the project’s GitHub page, the SK extensible programming model brings together natural language semantic functions, traditional code native functions, and embeddings-based memory in order to access new potential and add value to apps with AI.

SK was designed to support and include design patterns from recent AI research, allowing developers to enrich their applications with complicated skills such as prompt chaining, recursive reasoning, and summarization.

Furthermore, users can infuse their apps with zero/few-shot learning, contextual memory, long-term memory, embeddings, semantic indexing, planning, and accessing external knowledge stores as well as the users own data.   

“By joining the SK community, you can build AI-first apps faster and have a front-row peek at how the SDK is being built. SK has been released as open-source so that more pioneering developers can join us in crafting the future of this landmark moment in the history of computing,” the project maintainers wrote on SK’s GitHub page.

Additionally, SK supports prompt templating, function chaining, vectorized memory, and intelligent planning capabilities out of the box.

More information is available in the documentation.  

The post SD Times Open-Source Project of the Week: Semantic Kernel appeared first on SD Times.

“With AI available at every step, we can fundamentally redefine developer productivity. We are reducing boilerplate and manual tasks and making complex work easier across the developer lifecycle. By doing so, we’re enabling every developer to focus all their creativity on the big picture: building the innovation of tomorrow and accelerating human progress, today,” Thomas Dohmke, CEO of GitHub, wrote in a blog post. 

The new chat capabilities are intended to provide a “ChatGPT-like experience” in the editor. It natively integrates into VS Code and Visual Studio and can recognize code that has been typed and what error messages are shown, enabling it to provide analysis on what the code blocks are intended to do, generate unit tests, and provide bug fixes. 

There is also a voice component to this that will enable developers to give prompts by speaking. 

Another part of Copilot X is that it will be able to generate descriptions of tags and descriptions for pull requests. The company is also working on a feature where it will warn developers if a pull request doesn’t have sufficient testing and then suggest potential tests. 

Copilot is also being integrated into documentation, with a chat interface that will allow developers to ask questions about the languages, frameworks, and technologies that their code is using. It has already created this functionality for React, Azure Docs, and MDN documentation, and plans to also bring this to internal documentation as well.  

“From reading docs to writing code to submitting pull requests and beyond, we’re working to personalize GitHub Copilot for every team, project, and repository it’s used in, creating a radically improved software development lifecycle,” Dohmke wrote.

The post GitHub Copilot X brings chat functionality to improve coding experience appeared first on SD Times.

“At its core, Microsoft Loop is about people—people who want to create together with ease, no matter where they are or what tools they use. It’s a transformative co-creation experience that brings together teams, content, and tasks across your tools and devices,” Wangui McKelvey, general manager at Microsoft, wrote in a blog post. 

The app is built to make it easier for teams to collaborate on projects and co-create content in real-time. Users can add a workspace title and any other relevant keywords, and Microsoft Loop will suggest the most relevant pieces to add to the workspace. New pages can easily be started with templates and drag-and-drop pages or blocks of content.

When users want to share pieces of information, they can turn any content on a Loop page into a component and copy and paste it across Microsoft 365 apps including Teams chat, Outlook, Whiteboard, and soon to Word for the web. They can also share whole pages either as a link or a live page. 

Loop also includes features like AI-powered transcription and translation for seamless communication across different languages. Microsoft 365 Copilot – which was announced last week – in Loop gives users AI-powered suggestions to help transform the way you create and collaborate by guiding them with prompts like create, brainstorm, blueprint, and describe. Or simply type in a prompt, like “help me create a mission statement.”

The app is available for Microsoft 365 subscribers and can be accessed through the Teams desktop and mobile apps and a web browser. The app is set to roll out to users in the coming months.

The post Microsoft launches public preview for Loop to drive better team collaboration appeared first on SD Times.

According to the company, this release is a way to move to the next evolution of code abstraction, transitioning from custom code to low-code to natural language authoring where humans and machines can work side by side to build apps.

After the initial natural language prompt, users can have a conversation with Copilot to make necessary adjustments to the app, such as adding columns to data tables.

Furthermore, Copilot in Power Apps offers users proactive recommendations for how they can improve their applications if they feel stuck on where to go next.

This release also offers improvements to the way users query and interact with their data so they can gain intelligent insights about their data in their apps through a conversational chat experience. 

Users can use natural language to create queries and fine tune their analysis whether they need to make sense of changes in their inventory, estimate the average time needed to complete a task, or explore which campaign generated the most revenue. 

Microsoft has also announced a native integration of AI-empowered Power Virtual Agents into Power Apps. With this, developers can add a next-generation AI-powered Power Virtual Agents bot to their applications. 

To do this users must turn on the control and enter the Power Virtual Agents bot schema name and then the Power Virtual Agents bot will have access to the most recent Power Virtual Agents features such as conversation booster and natural language bot building.

For more information, read the blog post. 

The post Microsoft introduces AI copilot in Power Apps to improve low-code development appeared first on SD Times.