Code Conversations

The roles of programmers and designers are evolving. The convergence of design and code signals a narrowing gap, prompting us to question the future landscape of design. As we enter the age of AI, will this lead us to chart a new course, or will it see us walking down familiar paths?Drawing from her experience leading Design at GitHub, she’ll delve into her journey starting out as a designer who codes, to building and leading teams of hybrid designer-developers. She'll examine how blurring the traditional boundaries between design and engineering has shaped the role of Design Engineering in the future of software design. Join her as she explores the dynamic interplay between AI, design, and programming, and consider the exciting possibilities that lie ahead.

Ref: https://www.youtube.com/watch?v=3fu3nvOYs8Q&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=49

Retrieval augmented generation (RAG) provides large language models with up to date information and helps them hallucinate less. But how does it all work beneath the covers?In this live coding session we'll build the components of a RAG system from scratch. (Aside from the LLM, there probably isn't time for that!) By building our own, we'll understand vectorisation, similarity search, and the role of embedding models and vector databases. We'll then plug it all together to see our augmented bot in action.You'll get a good grounding in the components of successful chatbots and why they work.

Ref: https://www.youtube.com/watch?v=wkvGcbsZmPo&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=48

AI is transforming the way Security Operations Centers (SOCs) work, and as a SOC engineer, your role is evolving fast.

Ref: https://www.youtube.com/watch?v=CaZbsbKnOho&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=47

Cybersecurity is rapidly evolving, shaped by artificial intelligence (AI) and the emergent potential of Quantum Computing.AI enhances security through automated detection and analysis, swiftly processing vast amounts of data to spot and predict threats, and Quantum Computing holds the promise to revolutionize various industries by offering unparalleled computational speed and efficiency, enabling it to tackle complex problems far beyond the reach of classical computers.Yet, these benefits also come with risks: AI's capabilities can be exploited for advanced phishing, vulnerability discovery, and creating adaptive malware, complicating the cybersecurity landscape, while Quantum Computing further challenges digital security by threatening to undermine traditional encryption, making existing protections potentially obsolete.This session will explore the mixed impact of AI and Quantum Computing on Cybersecurity, highlighting both the advancements and vulnerabilities they introduce. We'll discuss current threats like supply chain attacks and ransomware, alongside the integration of Privacy Enhancing Technologies (PETs) with AI and quantum defenses, offering a strategic viewpoint on safeguarding against the future of cyber threats.

Ref: https://www.youtube.com/watch?v=C9IgEfYCwFo&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=46

With GenAI, developers are shifting from traditional code reuse to generating new code snippets by prompting GenAI, leading to a significant change in the ways software gets developed.Several academic studies show that AI generated code based on LLM's that are trained on vulnerable OSS implementations lead to vulnerable generated code. Another study showed that developers tend to trust GenAI created code more than human created code. Combining that with the higher code velocity it will result in more vulnerabilities in it's output.Using an AI system that runs an LLM also has additional risks tied to it, related to jailbreaks, data poisoning and malicious agents, recursive learning and IP infringements.In this presentation, we will examine real-world data from several academic studies to understand how GenAI is changing software security, the risks it introduces, and possible strategies to address these emerging issues.

Ref: https://www.youtube.com/watch?v=krDJlrw5mM0&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=44

In the past year, ChatGPT and the OpenAI API have gone from 0 to 100 faster than a Tesla. No one wants to be left behind. Businesses are automating tasks and having content written instantly.Some companies are suddenly ✅ 10x more productive, and some companies ❌ struggle.SSW consultants have been leveraging AI to improve client’s products…. And solving problems inside SSW too. Let’s take a look at the best ones!The advent of Custom GPTs has meant problems that would have taken weeks to solve before, can have production ready solutions in hours.Semantic Kernel then allows you to build enterprise solutions that take advantage of LLMs in a structured and scalable way, enabling the integration of AI into various business processes and systems.

Ref: https://www.youtube.com/watch?v=upUZAZljueI&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=28

Web developers: you have a fantastic opportunity to make your web UIs more intelligent and productive than before. But don’t just throw on a chat pane and call it done, as people may not even use or like it. Let's explore how language models can integrate into your existing web UIs, anticipating your users' needs and completing their tasks faster.This is a technical, demo-centric talk with examples in Blazor, MVC/Razor Pages, and plain old C#, but the concepts would apply in other stacks too. We’re not going to get into the depths of how large language models (LLMs) work internally, nor will we focus on specifics of OpenAI APIs. Instead, we’ll focus on practical, complete, end-to-end usage patterns for AI in web UIs, making your users happier and more productive.

Ref: https://www.youtube.com/watch?v=TSNAvFJoP4M&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=29

In this session, we will explore what this model can do, and rather than just showing a perfect polished final demo, I will walk you through my entire journey of trying to use the model to solve Wordle puzzles, starting with "Hello World". Along the way, you will gain a good understanding of the model's capabilities, along with learning some prompt engineering techniques that drove progress in this journey (along with what didn't work!). We'll close with a live demo to attempt to solve today's Wordle! This session will tackle a fun problem, but the underlying prompt engineering techniques for image understanding that you will learn are applicable to a wide variety of business problems.

Ref: https://www.youtube.com/watch?v=sfpk4wQeS_g&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=37

The focus upon AI continues to be the predominant technology subject of the day; it’s the must-have feature of any new product or service; it’s at the forefront of many discussions about ethics, attribution and indeed our own future employment prospects.But increasingly, the term “AI” has become synonymous with only one flavour of artificial intelligence - that being “machine learning” (ML) - e.g. generative AI, applied AI, large language models (LLMs) and the such.However, there are many other types of AI, which until recently, were the mainstay algorithms found behind automated decision making solutions.Many of these concepts can be found in the video games we know and love.Are these other types of AI still relevant? Do they risk being drowned out, or forgotten, in the rush to embrace machine learning solutions?In this session, intended for the enterprise/business application developer, we’ll open a window into the world of the video game development.We’ll explore the type of algorithms that are a staple of game development: pathfinding, state machines, decision trees, and goal-oriented action planning.We’ll delve into some of the performance considerations necessary to keep these algorithms running efficiently.We’ll circle back to how the business application developer can use this type of AI in applications, and how the lessons learnt making video games can help us write better software.

Ref: https://www.youtube.com/watch?v=w30cK2ga42M&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=36

AI CoPilots are all the rage - but none quite offer that personalised butler service SciFi told us we might one day have.To understand what it takes to train a CoPilot, we will see how training a model works under-the-hood; discuss the importance of quality training data to craft a truly powerful and personalised experience, and safety or security concerns to consider when training a model on a public service.Moving beyond the (chat) box, we will leverage Azure's OpenAI Service and Semantic Kernel in .NET to create a custom AI CoPilot for internal applications or data. We will see how to train our own custom Codex model, for generating code and commands to perform bespoke tasks against a non-public API, plus some innovative ways to glue this together with a nice user experience.You will leave feeling excited about the power of custom CoPilots, and armed with the knowledge to build your own!

Ref: https://www.youtube.com/watch?v=QXPlIYd408A&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=35