With advanced generative AI systems reshaping software development, Microsoft's Mads Kristensen detailed the many ways AI will improve coding in Visual Studio.
With Google recently releasing a generative AI-powered search bot called Bard to rival Microsoft's "new Bing" search experience, we put both to the test, feeding them identical questions about Visual Studio and .NET.
GPT-4, the advanced generative AI model from Microsoft partner OpenAI, is now powering the new GitHub Copilot X and the Azure OpenAI Service.
A new tool that can generate code is being previewed in the Visual Studio Code Insiders channel seeks to ease the tedious data preparation process that data scientists need to go through to get good data for successful analysis projects.
Decision trees are useful for relatively small datasets that have a relatively simple underlying structure, and when the trained model must be easily interpretable, explains Dr. James McCaffrey of Microsoft Research, who provides step-by-step instructions and full source code.
Microsoft has open sourced an internal incubation project that can help developers integrate cutting-edge AI models quickly and easily into their apps.
Power Platform "is reinventing software development with AI-powered no-code development."
Prompt engineering has recently become popularized with the advent of cutting-edge generative AI constructs based on the GPT-3 series of large language models (LLMs) created by Microsoft partner OpenAI.
ChatGPT, the hottest tech in the industry, is now available in the Azure OpenAI Service as a preview, Microsoft announced today, March 9.
With new generative AI tools shaking up the software development space, there are now more than 400 AI-infused extensions in the Visual Studio Code Marketplace.
Dr. James McCaffrey of Microsoft Research shows how to predict a person's sex based on their job type, eye color and country of residence.
"Our new unit test generation capability uses cutting-edge AI technology to generate unit tests for your code automatically."
With AI all the rage these days in the development space and elsewhere, Microsoft touted new machine-learning-powered intent-based suggestions in this week's release of Visual Studio 2022 17.5.
Dr. James McCaffrey of Microsoft Research says decision trees are useful for relatively small datasets and when the trained model must be easily interpretable, but often don't work well with large data sets and can be susceptible to model overfitting.
Developers continue to claim -- as they have for years -- that the "AI pair programmer" GitHub Copilot tool doesn't work well with IntelliSense, which is built in to Visual Studio and Visual Studio Code.
GitHub has again upgraded the AI tech behind its Copilot "AI pair programmer," which reportedly already generates 61 percent of Java Code in editors where it's used and 46 percent across all languages.
"We've also added a new AI Tools in VS Code topic to the VS Code documentation that will help you get started with Copilot."
Dr. James McCaffrey of Microsoft Research says the main advantage of scikit is that it's easy to use (even though most classes have many constructor parameters).
With ChatGPT being the first "It" tech in the cutting-edge AI space that regular people can play around with, it's no wonder that tools to use it are exploding in the Visual Studio Code Marketplace.
The fundamental technique has been studied for decades, thus creating a huge amount of information and alternate variations that make it hard to tell what is key vs. non-essential information.
"We wondered how we could make editing your code feel as tactile and easy as paint with a brush in Photoshop."
Dr. James McCaffrey of Microsoft Research: When multi-class data is skewed toward one or more classes, it's very important to analyze accuracy by class.
Dr. James McCaffrey of Microsoft Research uses full code samples to detail an evolutionary algorithm technique that apparently hasn't been published before.
Dr. James McCaffrey of Microsoft Research says that when quantum computing becomes generally available, evolutionary algorithms for training huge neural networks could become a very important and common technique.
Heading the highlights of ML.NET 2.0 are new APIs for working with text, specifically text classification in Model Builder, along with a sentence similarity API.
> More Webcasts