From Me
Happy Friday everyone!
If you caught this past week’s MSI Show (Microsoft Security Insights Show Episode 207 - Forsyte), you heard about my wife’s experience with a Goose and our vehicle. For more to the story, the car is in the shop, and they are suggesting that it might take about a month to get parts to repair just because of how hard it is to get parts. The type of accident gave many at the repair shop and the tow truck service much to laugh and talk about.
So, we’re in the market for a new car. I’ve never used any of the self-buy programs like Carvana but am open to it. I’d be happy to hear your experiences with these programs. If the experiences have been good, we may opt to do that instead of spending hours shopping local.
…
If you remember, I hosted a subscriber poll for both the Microsoft Sentinel and Defender weekly newsletters last week and the response was overwhelmingly positive to start a newsletter about Copilot for Security. Go figure!
So much so, that I've already started the process. Called "The CfS Prompt" the newsletter will start out with bi-weekly delivery and is designed to capture all the great content delivered by Microsoft, Microsoft MVPs, and the community at large. The newsletter will begin delivery on Friday, May 3rd.
Subscribe here to be a Founding Member:
With the advent of The CfS Prompt, the Copilot for Security content here and in the Defender newsletter will be able to be more fine-tuned and focused. So, if you’re looking for all the great Copilot for Security content, you’ll need to subscribe or watch there.
…
For those that attended (and didn't attend) the beta workshop for Prompt Engineering for Copilot for Security last week, the current deck is here:
https://github.com/rod-trent/Copilot-for-Security/tree/main/Prompts/Workshop
At around 89 slides currently, this is a work in progress and has been updated a couple times already. The final version will be available for both internal and external partners and will be updated at this location.
Additionally, I will be recording a Ninja Training series episode for this in the coming days. So, Prompting for Copilot for Security is coming to the Ninja Training series! Stop by to hear about this upcoming workshop content.
May 15 at 9:00AM (PT) - Add it to your calendar: https://aka.ms/NinjaShow/S8Ep4/calendar
Check out all the upcoming shows: https://adoption.microsoft.com/ninja-show/
…
That’s it from me for this week.
Talk soon.
-Rod
From My AI
This week I asked my AI for tips on how to avoid geese on local roads. Here’s the response…
Here are some tips on how to avoid geese on highways and roads:
Slow down: If you see geese on the road, slow down to avoid hitting them. Geese can be unpredictable, so it's best to err on the side of caution.
Use your horn: If you see geese on the road and they're not moving, you can use your horn to encourage them to move out of the way.
Avoid sudden movements: If you need to swerve to avoid geese, do so gradually and avoid sudden movements that can cause you to lose control of your vehicle.
Stay alert: Keep an eye out for geese, especially near waterways and parks. Geese are often found in these areas and can wander onto roads.
Watch for signs: Some areas may have signs warning drivers of geese crossings. Pay attention to these signs and adjust your driving accordingly.
Remember to always drive safely and be aware of your surroundings to avoid accidents involving geese or other wildlife.
From Microsoft
Join the Microsoft Developers AI Learning Hackathon and Win Up to $10K in Prizes! - Join the Microsoft Developers AI Learning Hackathon for a chance to hone your AI skills, build an AI copilot with Azure Cosmos DB for MongoDB, and compete for up to $10,000 in prizes.
Unveiling Generative AI Bulk Processing and Ingestion Pattern - This technical blog describes a pattern for bulk processing and ingestion with generative AI, which can help organizations grow their generative AI solutions from prototype and proof of concept phases to pilot and production workloads.
Build Intelligent RAG For Multimodality and Complex Document Structure - The advent of Retrieval-Augmented Generation (RAG) models has been a significant milestone in the field of Natural Language Processing (NLP). These models combine the power of information retrieval with generative language models to produce answers that are not just accurate but also contextually enriched. However, as the digital universe expands beyond textual data, incorporating image understanding and hierarchical document structure analysis into RAG systems is becoming increasingly crucial. This article explores how these two elements can significantly enhance the capabilities of RAG models.
Improving RAG performance with Azure AI Search and Azure AI prompt flow in Azure AI Studio - If you've been delving into the potential of large language models (LLMs) for search and retrieval tasks, you've probably encountered Retrieval Augmented Generation (RAG) as a valuable technique. RAG enriches LLM-generated responses by integrating relevant contextual information, particularly when connected to private data sources. This integration empowers the model to deliver more accurate and contextually rich responses.
Unlock the Power of Small Language Models with Phi-3 and Azure AI Studio - As a technical student, you're likely fascinated by the rapidly evolving world of artificial intelligence (AI) and machine learning. In this blog, we'll explore the exciting realm of Small Language Models (SLMs), a new breed of AI models that are redefining what's possible with Azure.
Build your first ML-Model with ML.NET Model Builder - In this step-by-step guide, I'll walk you through the process of building your first machine learning model using ML.NET Model Builder within Visual Studio 2022. From setting up your development environment to training and evaluating your model's performance, each step is meticulously outlined to ensure a smooth and rewarding experience.
Image Analysis with Azure Open AI GPT-4V and Azure Data Factory - Since the first article was published, I have added image analysis to the ADF solution and have made it easy to deploy to your Azure Subscription from our Github repo, AI-in-a-Box, using azd.
Getting Started - Generative AI with Phi-3-mini: A Guide to Inference and Deployment - Maybe you were still paying attention to the Meta Llama 3 released last week, but today Microsoft did something different and released a new Phi-3 series of models.
Unlocking industrial data for AI: Microsoft partners with leading connectivity providers - Microsoft is partnering with leading industrial connectivity partners Advantech, PTC, and Softing to unlock industrial data for AI and accelerate digital transformation for industrial customers leveraging Azure IoT Operations through Azure’s adaptive cloud approach.
Data Discovery: The First Step to AI Readiness - In this blog series, we will explore these steps and provide recommendations for enterprises to prepare their data for AI.
A Heuristic Method of Merging Cross-Page Tables based on Document Intelligence Layout Model - This blog provides a heuristic approach to identifying and merging tables, this process accounts for a few different variations including vertical or horizontal cross-page tables, tables with repeating headers or continuation cells. The output can then be fed into the LLM for improved context resulting in more relevant and accurate responses. In future updates the layout model will support cross-page tables.
From Others
OpenAI Security Bots - Slack bots integrated with OpenAI APIs to streamline security team's workflows.
Breaking Free from the Short Query Mindset and Embracing In-Person Conversations with an AI Copilot - In today's digital age, search engines have become an integral part of our lives. We rely on them to find information, discover new products, and connect with the world. However, the traditional search engine mindset, which focuses on short queries and keyword matching, has its limitations. It often fails to understand the nuanced intent behind a user's search, leaving us with subpar results. But what if there was a way to bridge this gap? What if we could have in-person conversations with search engines to truly understand our needs? This is where AI copilots come into play.
The Advantages of Engaging with an AI Copilot for Research: A Smarter Alternative to Search Engines - Traditionally, search engines have been the go-to tool for gathering information. However, they have their limitations. This is where AI copilots come in.
Revolutionizing Language Learning: How Generative AI is Preserving the Art of In-Person Communication - Generative AI, also known as Artificial Intelligence, has revolutionized many industries, and language learning is no exception. It uses algorithms and machine learning to generate human-like language and responses. This technology has the potential to transform the way we learn and preserve languages, especially in the context of in-person communication.
Safeguarding Your Digital Assets: The Crucial Role of Data Security in the AI Era - In the rapidly evolving landscape of technology, artificial intelligence (AI) has emerged as a game-changer. With its ability to process vast amounts of data and make intelligent decisions, AI has revolutionized industries across the board. However, as we embrace the power of AI, it is crucial to recognize the importance of data security in protecting our digital assets. In this article, I will delve into the role of data security in the AI era and discuss best practices, regulations, encryption, tools, and training to ensure a secure future.
Unlocking Data Security in the AI Era with Microsoft Purview - In today's digital landscape, data security has become a paramount concern. With the rise of artificial intelligence (AI) and its applications in various industries, protecting sensitive data has become more challenging than ever. Organizations are now faced with the task of not only harnessing the power of AI but also ensuring that their data remains secure throughout the process. This is where Microsoft Purview comes into play.
From the Industry
Cool or creepy? Microsoft's VASA-1 is a new AI model that turns photos into 'talking faces' - A new AI research paper from Microsoft promises a future where you can upload a photo, a sample of your voice and create a live, animated talking head of your own face.
A new framework to generate human motions from language prompts - Machine learning-based models that can autonomously generate various types of content have become increasingly advanced over the past few years. These frameworks have opened new possibilities for filmmaking and for compiling datasets to train robotics algorithms.
Coca-Cola signs $1.1 bln deal to use Microsoft cloud, AI services - Under the agreement, Microsoft and Coca-Cola will "jointly experiment" with Azure OpenAI. That service uses technology from Microsoft-backed startup and ChatGPT creator OpenAI to let customers build chatbots and other AI services that run in Microsoft's Azure cloud computing service.
Microsoft launches lightweight AI model - Microsoft on Tuesday launched a lightweight artificial intelligence model, as it looks to attract a wider client base with cost-effective options.
Events
"Unlocking Infinite Potential with Microsoft Generative AI" - Boost Your Productivity, Efficiency, and Creativity with Generative AI, Azure AI Models, and Discover Microsoft’s Copilot Ecosystem
Join us for an enlightening series of sessions by registering through the link below: