This session covers the ethical use of AI, detailing how to identify, understand, and proactively counter potential risks while sharing examples of impactful solutions built for the nonprofit and humanitarian sectors. The discussion emphasizes the necessity of implementing responsible AI principles, utilizing mitigation strategies like prompt engineering and grounding, and acknowledging that AI will always make mistakes.
Ref: https://www.youtube.com/watch?v=odWIkRcqEAU&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=20
Large Language Models (LLMs), including GPT, operate at their simplest level by attempting to produce a reasonable continuation of the text they are given, basing their predictions on patterns observed across a massive corpus of information like billions of web pages. Prompt engineering is an iterative process that employs various techniques—such as role prompting, few-shot learning, and Chain of Thought prompting—to increase the accuracy, reliability, and personalization of the output, which helps minimize uncertainty and build trust in the generative AI technology.
Ref: https://www.youtube.com/watch?v=1XrgOK-Ydl8&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=19
Recent advances in generative AI, exemplified by LLMs like Stable Diffusion and ChatGPT, have created significant industry hype. Generative AI involves creating new media (such as text or images) by analyzing massive datasets to deduce and mimic existing patterns, a process driven by probabilistic and stochastic modeling. While models like GPT can produce humanlike text, they operate as language prediction models rather than utilizing true reasoning (AGI), which means they often "stumble over facts," produce inconsistent results, and struggle with basic tasks like multiplication, leading to "hallucinations". To leverage these tools effectively, prompt engineering is necessary—this "subtle art" involves providing clear, specific instructions, setting a system context or persona, and potentially using examples to coax a useful result from the AI. When integrating AI via the stateless Completions API, developers must manually maintain conversation state by sending the entire history with each request, often summarizing older messages to manage token costs. More robust applications can utilize GPT Functions (Tools) to allow the model to intelligently call external functions—avoiding expensive model retraining—to access live or proprietary data. Alternatively, to query custom data using natural language, facts can be converted into high-dimensional vectors called embeddings and compared using cosine similarity against user queries, often managed in a database like Postgress with PG Vector. Finally, the newer Assistants API simplifies the development of domain-specific helpers by automatically managing message history and context compaction, and uniquely, when referencing uploaded knowledge files (like a lease document), it provides specific references or footnotes detailing where the answer was found.
Ref: https://www.youtube.com/watch?v=OxHw_u45h7M&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=18
Enterprise software development is currently facing immense executive pressure, driven by boards and CEOs demanding rapid innovation, especially utilizing AI, to increase productivity, save costs, and gain a competitive advantage, a significant shift from previous executive disinterest in issues like integration modernizations. Developers frequently encounter frustrations and delays, including the "age old disconnect" where their pursuit of new tools clashes with IT and Security's focus on uptime, reliability, and avoiding security breaches, leading to delays of months in realizing business value after writing working code. This inefficiency is exacerbated by the extensive time spent on environment setup, sometimes weeks, which the speaker suggests "should be illegal" given the cost of developer time. To address these challenges, modern tooling focuses on standardizing environments: GitHub Codespaces provides an ephemeral, standardized development environment (VS Code in the browser connected to backend compute) where mean time to onboard can be reduced to minutes, defined by a devcontainer.json file that specifies necessary dependencies; complementarily, Dev Box offers full, on-demand virtual machines based on team-defined templates, which are highly supported by security teams because they are built on existing tooling (like Windows 365 and InTune) and allow for customized security profiles that can exclude productivity apps (a common attack vector), helping one customer reduce environment setup time for .NET applications from over two weeks to three hours. Further accelerating delivery involves codifying Deployable Architectural Archetypes using the Azure Developer CLI (azd), a principle that dictates repositories contain source code alongside infrastructure-as-code (Terraform or Bicep) and CI/CD pipelines, ensuring critical elements like Key Vault and Azure Monitor are "baked in" from the start. This approach is key to engaging security, architecture, and infrastructure champions early, transforming them into innovation accelerators by incorporating their requirements into the blueprint templates, allowing deployment of full infrastructure and applications with simple commands like azd up. Ultimately, while tools like these, along with GitHub Co-pilot for Business (which securely boosts performance by 30% to 50%), help "grease the wheels," successful acceleration relies on ensuring the people and process are right, including having security champions on the team and deploying applications to secure, compliant Landing Zones.
Ref: https://www.youtube.com/watch?v=mTozV_eV4jQ&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=17
This presentation by Mandy Michael, a Staff Software Engineer and Google Developer Expert, makes a compelling case for using HTML meaningfully to improve web performance and accessibility, arguing that these concerns should be addressed from the foundational HTML stage, not left until the end of development. The core message is that HTML elements should be chosen based on the content type—similar to using types in TypeScript—rather than relying excessively on generic div elements, because correct semantic HTML creates a crucial Document Object Model (DOM) and Accessibility Tree that is consumed by assistive technologies and search engines. Michael provides practical HTML tips, such as favoring native element functionality (like using <button> instead of a styled <div>) for built-in features and using attributes like fetchpriority, loading="lazy", and resource hints (preload, preconnect) to effectively optimize resource loading and improve performance metrics like Cumulative Layout Shift (CLS) and Largest Contentful Paint (LCP).
https://youtu.be/zA4QzRGIP_w?list=TLGGh5u1cryB-zYwNzEwMjAyNQ
This speech synthesis service allows you to train your own model based on existing base models, utilizing a neural Voder to generate speech from text input. Crucially, Microsoft promotes responsible use: every custom voice must provide a talent statement (consent) that expires after 90 days.
https://youtu.be/XkbvfSLO3yE?list=TLGGiewzlim6miMwNzEwMjAyNQ
This talk was recorded at NDC Sydney in Sydney, Australia.
Ref: https://www.youtube.com/watch?v=odWIkRcqEAU&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=20
To trust or not to trust? That depends on the quality of your prompts. Trusting Large Language Models (LLMs) is all about reducing uncertainties, and effective prompt design is the key to achieving the desired outputs.Prompt design, often referred to as Prompt Engineering, is a burgeoning field that demands creativity and meticulous attention to detail. It involves carefully selecting the right words, symbols, patterns, and formats to guide the LLMs in generating high-quality and relevant texts for the tasks at hand.
Ref: https://www.youtube.com/watch?v=1XrgOK-Ydl8&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=19
People talking about AI is like glitter after a craft project, or azulejos in architecture, it's everywhere! Recent advances in generative AI, like Stable Diffusion and Chat-GPT, have the industry more hyped up than a caffeine-addicted toddler. It can leave one feeling like they're being left behind if they're not incorporating AI into their apps today.In this talk, we'll take a sober look at the topic of Generative AIs. In particular, we'll look at how Large Language Models (LLMs) work and where they break down. We'll consider how to engineer prompts for AI. And finally, we'll look at practical examples of adding AI into into a real-world app based on my experiences introducing AI into https://ab.bot/, an app designed to help customer success teams support their customers. We'll write code that calls Open AI APIs that demonstrate how to sprinkle a little AI into your own app. Join us to learn how to leverage the latest advancements in generative AI and take your applications to the next level.
Ref: https://www.youtube.com/watch?v=OxHw_u45h7M&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=18
The landscape of software development is rapidly evolving, and developers are constantly seeking better tools to enhance their productivity and create more efficient workflows. In this talk, I'll show you what many of my enterprise customers are looking to implement - deploying architectural archetypes using the latest advancements in developer toolsets.We will stand up our dev environment on Azure DevBox and GitHub Codespaces, use the Azure Developer CLI to deploy the templates, leverage GitHub CoPilot for AI-powered code generation to deploy an architecture including the Azure OpenAI API for integrating machine learning and natural language processing into applications - and we'll easily do it in 60 minutes.Come along for a hands-on tour of the latest in developer tooling.
Ref: https://www.youtube.com/watch?v=mTozV_eV4jQ&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=17
It's been hard to miss AI in the news recently. From breakthroughs in natural language processing to impressive image recognition and generation capabilities, AI is everywhere we look right now!In this talk, experienced software engineer Simon Waight will explore the benefits and considerations for developers when they are looking to adopt generative AI as part of their toolkit.To help set the scene, there will be a brief introduction to the fascinating world of generative AI and how it fits into AI more broadly.We'll then look at how generative AI can aid developers in streamlining their workflows and enhance productivity. How about instead of manually creating solutions from scratch, developers could utilise generative models to automatically generate prototypes, designs, or code snippets? How about in a programming language they don't even know?!But there are risks, which we'll explore along the way to ensure everyone is making informed decisions about adopting this technology that has massive positive potential.Finally, all talk and no demo sessions aren't fun, so we'll also do some audience-interactive live coding with a couple of scenarios that will demonstrate the value of this new technology.
Ref: https://www.youtube.com/watch?v=j_NsChKERh8&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=16
Microsoft Security Copilot leverages with the full power of Generative AI with specially trained models focused on Security Operations within a Microsoft Security environment.Attend this session to go on a deep dive for Microsoft Security Copilot. Learn how it can assist security operations teams to prioritise workloads, facilitate incident response and remediation, understand how it can assist on understanding best practice to manage environments in ways to reduce the likelihood of repeat successful attacks.
Ref: https://www.youtube.com/watch?v=cCUMJ9ywfuQ&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=25
Embark on a journey with an introverted developer who discovered the secret to combatting imposter syndrome, doing epic shit, and forging meaningful connections in the global tech landscape (mostly from behind the keyboard).In this session while we see how GitHub CoPilot helps developers write better code, understand complex codebases, and solve problems differently. We'll talk about workplace anxiety, diversity of thought, and the importance of incorporating responsible AI principles into your life and your code.Get ready to unlock the code that leads to a truly successful journey!
Ref: https://www.youtube.com/watch?v=5Tg9leLR3fE&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=24
"Hey AI, build me a production ready, secure, scalable, monitored, customer facing system driven by an LLM"In this session we will look at the architectural patterns and practices required to drive production-ready systems backed by large language models, considerations around content filtering, approaches to stop your enterprise bots leaking secrets as a pirate sea shanty, and how to leverage services like OpenAI ChatGPT and Azure OpenAI.
Ref: https://www.youtube.com/watch?v=hn2Dn3fLIfg&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=23
HTML is not just the foundation we build on, its vital in making our websites accessible usable and performant.We'll explore how we can make the most of our HTML elements and attributes to improve the performance and accessibility of our website and applications as well as boosting the efficiency of our development process.All by using a technology we are already use day to day, but just using it better than we were before. At the end of the talk you'll be able to make things more useful and useable, not just for performance and accessibility but for our users and different technologies, likes bots, applications and AI as well.
Ref: https://www.youtube.com/watch?v=zA4QzRGIP_w&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=22
Everyone has at some point wished they could clone themselves – to do the dishes, or work more efficiently. With advancements and improved accessibility of AI, this becomes more of a reality...This session will explore how to use Azure Custom Neural Voice to create a synthesised version of our own voice for use in a range of fun and practical applications – telephony, voice overs, or even attending meetings on your behalf...!We'll cover the basics of training and tweaking a model of our own voice, with minimal code, that can be used to turn text into natural-sounding speech.Advancing further, we'll learn some ways to train our model with enhanced training data. As an example we'll take a larger amount of audio, such as a podcast, use widely available tools and APIs to identify the individual speakers and the words being spoken – including highly technical language – to feed into our model.You will leave with the knowledge and inspiration to give "cloning" your voice a try!
Ref: https://www.youtube.com/watch?v=XkbvfSLO3yE&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=21
Join Michael Tjalve from Microsoft Philanthropies and the University of Washington as he explores the ethical use of AI, delving into how to best leverage this powerful technology while understanding and proactively countering its potential risks and consequences.
In this insightful discussion, Michael draws on his extensive work with nonprofit and humanitarian organizations worldwide, revealing how AI is being applied to achieve real-world, societal-scale impact. You'll hear specific examples of projects that address critical global challenges, such as:
The conversation also demystifies how AI works, from its ability to simulate human abilities like seeing, perceiving, and reasoning, to the breakthroughs in deep learning and generative AI. Michael explains why AI is so prominent now, attributing its rapid advancement to the availability of vast amounts of data, cloud computing, and more efficient algorithms.
Crucially, the episode addresses the inherent risks and concerns surrounding AI, including data privacy, potential job displacement, and the phenomenon of "hallucinations" – where AI can be confidently inaccurate, leading to misinformation. You'll learn about Microsoft's responsible AI principles, which have evolved from design philosophies into tangible engineering processes, and the importance of self-regulation in a fast-moving AI landscape.
Discover practical mitigation strategies like prompt engineering – a vital skill for effectively interacting with AI models – and explore tools such as content safety features and responsible AI dashboards. Michael emphasizes the necessity of a "human in the loop" for high-stakes applications and reveals the rigorous approval processes for sensitive AI services like voice cloning and facial recognition, due to their potential for misuse.
This episode underscores that in an era of societal-scale disruptive technology, "running fast and breaking things" is not an option. Instead, the focus is on significantly reducing risks, understanding AI's decision-making and mistakes, and recognizing that the biggest limitation to AI's potential is often our own imagination.
Ref: https://www.youtube.com/watch?v=odWIkRcqEAU&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=20
To trust or not to trust? That depends on the quality of your prompts. Trusting Large Language Models (LLMs) is all about reducing uncertainties, and effective prompt design is the key to achieving the desired outputs.Prompt design, often referred to as Prompt Engineering, is a burgeoning field that demands creativity and meticulous attention to detail. It involves carefully selecting the right words, symbols, patterns, and formats to guide the LLMs in generating high-quality and relevant texts for the tasks at hand.We will write live prompts - taking input from the audience, and improving it on the fly!
Ref: https://www.youtube.com/watch?v=1XrgOK-Ydl8&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=19
People talking about AI is like glitter after a craft project, or azulejos in architecture, it's everywhere! Recent advances in generative AI, like Stable Diffusion and Chat-GPT, have the industry more hyped up than a caffeine-addicted toddler. It can leave one feeling like they're being left behind if they're not incorporating AI into their apps today.In this talk, we'll take a sober look at the topic of Generative AIs. In particular, we'll look at how Large Language Models (LLMs) work and where they break down. We'll consider how to engineer prompts for AI. And finally, we'll look at practical examples of adding AI into into a real-world app based on my experiences introducing AI into https://ab.bot/, an app designed to help customer success teams support their customers. We'll write code that calls Open AI APIs that demonstrate how to sprinkle a little AI into your own app. Join us to learn how to leverage the latest advancements in generative AI and take your applications to the next level.
Ref: https://www.youtube.com/watch?v=OxHw_u45h7M&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=18
The landscape of software development is rapidly evolving, and developers are constantly seeking better tools to enhance their productivity and create more efficient workflows. In this talk, I'll show you what many of my enterprise customers are looking to implement - deploying architectural archetypes using the latest advancements in developer toolsets.We will stand up our dev environment on Azure DevBox and GitHub Codespaces, use the Azure Developer CLI to deploy the templates, leverage GitHub CoPilot for AI-powered code generation to deploy an architecture including the Azure OpenAI API for integrating machine learning and natural language processing into applications - and we'll easily do it in 60 minutes.Come along for a hands-on tour of the latest in developer tooling.
Ref: https://www.youtube.com/watch?v=mTozV_eV4jQ&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=17
