Artificial Intelligence
Artificial Intelligence | News, how-tos, features, reviews, and videos
3 ways to upgrade continuous testing for generative AI
As more CIOs and devops teams embrace generative AI, QA teams must also adapt their continuous testing practices to keep up.
Applying the lessons of open source to generative AI
The excitement and turmoil surrounding generative AI is not unlike the early days of open source, or the Wild West. We can resolve the uncertainty and confusion.
Building LLM applications with vector search in Azure Cognitive Services
Microsoft’s Cognitive Search API now offers vector search as a service, ready for use with large language models in Azure OpenAI and beyond.
Zenhub previews AI for software project management
Zenhub is adding AI capabilities to automate task labeling, prioritize work, estimate completion dates, and provide insights into challenges and blockages.
The looming battle over where generative AI systems will run
Putting AI on cloud versus on-premises systems may seem like a simple decision, but it's much more complex (and potentially expensive).
7 low code platforms embracing AI
Many low-code and no-code development and RPA platforms now include AI capabilities, often using a version of GPT.
How to take action against AI bias
Humans must be the custodians for preserving high-quality data as AI use continues to advance.
Understanding OneLake and lakehouses in Microsoft Fabric
Microsoft Azure’s new, unified data platform aims to be your one-stop shop for analytics and machine learning at scale.
Google Project IDX brings AI to cloud-hosted development environments
Google Cloud service combines Codey-powered AI assistance and templates for popular JavaScript frameworks in a cloud-hosted Linux VM. Google said support for Python, Go, and other languages is coming soon.
10 ways generative AI upends the traditional database
Generative AI isn't just for chatbots. Here are 10 ways AI and machine learning are transforming how we store, structure, and query data.
Generative AI and a new version of old programming
Prompt engineering is still telling a computer what to do. Studying large language models and the limits of generative AI will keep your job security.
What is generative AI? Artificial intelligence that creates
Generative AI models can carry on conversations, answer questions, write stories, produce source code, and create images and videos of almost any description. Here's how generative AI works, how it's being used, and why it’s more...
Salesforce Einstein Studio to help enterprises train generative AI models
Einstein Studio can also help enterprises connect their data from Salesforce Data Cloud to third-party AI offerings including Amazon SageMaker and Google’s Vertex AI for model training.
Tame your wild LLM with TypeChat
Large language models mean not having to use complicated regular expression handlers to turn text into data. Using TypeChat, you can ensure that that data is type-safe JSON.
Generative AI with LangChain, RStudio, and just enough Python
Here's how R users can get comfortable working with Python and LangChain, one of the hottest platforms for working with large language models.
The tug-of-war between optimization and innovation in the CIO’s office
Should budget go to innovations or fixing existing systems so they don’t bankrupt you? The future of your business may ride on the answer.
Low code AI with Power Apps and Power Automate
Microsoft's AI Builder introduces low-code generative AI capabilities to Power Apps and Power Automate. Let's see how the preview features stack up.
The open source licensing war is over
It’s time for the open source Rambos to stop fighting and agree that developers care more about software’s access and ease of use than the purity of its license.
Ease into similarity search with Google’s PaLM API
Learn how to use Google Cloud Vertex AI and the PaLM 2 large language model to create text embeddings and search text ranked by semantic similarity.
The lost art of cloud application engineering
AI-driven coding is now in wide use, but we may not know all the risks of using it until the damage has been done. Think security problems and code that wastes resources.