Shows
Code ConversationsChatGPT and OpenAI API solutionsIn 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 ente...2025-06-0615 min
Code ConversationsKubernetes and MLOps for Scalable and Reproducible Generative AICombining the power of Kubernetes and MLOps brings scalability, reliability, and reproducibility to generative AI workflows. In this session, we will explore how Kubernetes enables the orchestration of distributed generative AI training and inference pipelines, while MLOps practices ensure efficient model development, deployment, and monitoring. Join us to discover how this combination empowers organizations to unlock the full potential of generative AI while achieving seamless scalability and operational excellence.Ref: https://www.youtube.com/watch?v=DXxqqB3dkiw&list=PL03Lrmd9CiGey6VY_mGu_N8uI10FrTtXZ&index=112025-05-3115 min
Code ConversationsWhat comes after ChatGPT? Vector Databases - the Simple and powerful future of ML? - Erik BambergWhat comes after ChatGPT? Vector database projects like Weaviate, Pinecone, and Chroma recently got millions of dollars of funding for their projects. But what are vector databases? And why will they be so important in the future?Let us see how Vector Databases can help you define and run your machine learning business use cases. We will explore some real-world use cases and try to understand the potential of vectors and vector databases. A brief hands-on demonstration just using open source will give you an idea, of how to use the new generation of databases in praxis.We will also...2025-05-2421 min
Code ConversationsLevel up with GitHub Copilot: using AI to learn, code, and build - Michelle "MishManners" DukeIt's time you meet your AI pair programmer. Do you find yourself stuck on a chunk of code? Unsure of how best to center a div? GitHub Copilot can help. Get unstuck by seeing suggested lines or code, whole functions, and learn more about your development journey through having code explained, and even translate your code into other languages.Find out more about GitHub Copilot, new features, updates, and see a demo.The session will cover:What is AIApplications of AIHow GitHub Copilot worksHow to get better results from GitHub Copilot with prompt engineering (the art crafting effective...2025-05-1817 min
Code ConversationsNeural Style Transfer: Generative AI Art and ScienceNeural Style Transfer (NST) is a concept in generative AI where the content of one image is combined with the style of another to create a new image. It uses a pre-trained Convolutional Neural Network (CNN) and adds loss functions with style transformations to generate a novel image.CNNs are deep learning models used mainly in image analysis to understand image content. They work by using filters to detect features like lines, edges, shapes, and patterns in layers. Pooling helps to focus on the main object by disregarding redundant background information. Fully connected layers act as a...2025-04-1814 min
Code ConversationsTransformers and ChatGPT: The Rise of Generative AIAs software engineers, we have the incredible opportunity to harness the power of ChatGPT to elevate our applications to new heights of interactivity and intelligence. Embark on a thrilling journey through ChatGPT's evolution, powered by the Transformers architecture. Explore ChatGPT's real-world impact on code assistance, customer support, content generation, and more. But that's not all – there's more than meets the eye! We'll explore prompt engineering techniques and integration options using the OpenAI API. Roll out feeling inspired and ready to transform your applications and the world.https://www.youtube.com/watch?v=854xFUl-big2025-04-1520 min
Code ConversationsUnlocking the Potential of AIArtificial intelligence is rapidly changing the world we live in, and Microsoft is at the forefront of this exciting revolution. Join us for a session where we'll explore the latest innovation from Microsoft and GitHub on AI.Let's explore the latest technologies, including Azure OpenAI, Neural voice, and GitHub Co-pilot. With Co-pilot, an AI-powered coding assistant that suggests code snippets based on project context, developers can boost productivity. We'll also discuss the importance of developing AI in a way that benefits society as a whole.Don't miss this opportunity to learn and discover how you can leverage AI to...2025-04-1125 min
Code ConversationsExploring ChatGPT for Improved ObservabilityIn today’s fast-paced and complex technological landscape, observability has become a critical aspect of ensuring the reliability and performance of software systems.However, traditional observability tools and techniques can only go so far in providing insights into the behavior of these systems. Enter ChatGPT, a conversational AI tool that can help bridge the gap between observability and human understanding.In this session, we will explore ChatGPT and how it could theoretically be used to enhance an enterprise’s observability practices. We will briefly look at how ChatGPT can be trained to understand and interpret system logs, metrics, and othe...2025-04-0822 min
Code ConversationsBanking Cybersecurity: Battling DeepFakes & AI-powered ScammersJoin us in this gripping session as we peel back the layers of the banking sector's current state during these dark times. The industry faces relentless direct attacks and ingenious social engineering scams that have evolved with the digital era. As technology progresses, with the rise of DeepFake and powerful AI/ML tools like ChatGPT, scammers exploit these innovations, making cybersecurity an ever more critical pursuit.Representing a leading bank, we will share our first-hand experience of navigating these challenges and fortifying the protection of our customers' invaluable data and assets. Delve into the organizational hurdles we confronted from...2025-04-0421 min
Code ConversationsPrompt Injection: When Hackers Befriend Your AIThis is a technical presentation where we'll look at attacks on implementations of Large Language Models (LLMs) used for chatbots, sentiment analysis, and similar applications. Serious prompt injection vulnerabilities can be used by adversaries to completely weaponize your AI against your users.We will look at how so-called "prompt injection" attacks occur, why they work, different variations like direct and indirect injections, and then see if we can find good solutions on how to mitigate those risks. We'll also learn how LLMs are "jailbroken" to ignore their alignment and produce dangerous content.LLMs are not brand new, but we...2025-04-0121 min
Code ConversationsSoftware Engineering Careers 2025 RoadmapHere is a brief description for a post about how to kickstart your software engineering career, based on the source:A software engineering career can be started via bootcamps like TripleTen, which offer opportunities to gain practical skills.TripleTen is an online, part-time coding bootcamp that helps people transition into tech careers, even without prior experience. An advantage to TripleTen is that 87% of graduates are hired within 180 days.Bootcamps allow for a career and life change in less time and at a lower cost than a four-year college.TripleTen provides programs in software engineering, data science, cybersecurity, quality...2025-03-2526 min
Code ConversationsWhat It Takes To Be A Software EngineerSoftware engineering is more than just programming; it's about building software that works reliably, rooted in a pragmatic and scientific approach. The difficult part of software engineering is the design, given that production is as simple as cloning bytes. Software engineers should focus on exploration and discovery, adapting lessons from science through iteration, feedback, and incremental work. By working experimentally and empirically, engineers can manage the complexity inherent in software development. Modularity, cohesion, separation of concerns, abstraction, and coupling are key ideas that allow software engineers to compartmentalize systems, enabling easier changes and better understanding of code. Prioritizing these...2025-03-2112 min
Code ConversationsBecoming a Software EngineerSoftware engineers need a combination of hard and soft skills to be successful1. Hard skills are technical abilities learned through education or professional development that can be measured for proficienchttps://www.springboard.com/blog/software-engineering/skills-needed/2025-03-1813 min
Code ConversationsProduct Management Is Dead?Product management as we know it is over. AI is already dismantling the role faster than many of us expected. If you’re in product management, don’t be surprised by this; your job now is to adapt faster than the changes are happening.https://www.chatprd.ai/blog/product-management-is-dead2025-03-1414 min
Code ConversationsAI Agents into Product Management WorkflowsImagine an AI teammate that lives within your existing product management tools! An AI agent can boost your productivity by:Summarizing discussions in Slack.Generating PRD drafts.Answering questions about specs in Confluence.Suggesting priority changes in Jira.Creating simple web forms.Alerting you to drops in conversion rates.It integrates into your workflow, acting as a natural extension of your team. Stop switching between standalone apps and start working smarter! Deep integration will turn an AI agent from an occasional boost into an indispensable co-worker in the product development process.https...2025-03-1115 min
Code ConversationsKey Capabilities of an AI Product Management AgentAI Product Management Agents: Revolutionizing the Role of the Modern PMAI agents can act as an extra pair of hands and an extra brain across a Product Manager's core responsibilities.These agents offer key capabilities such as:AI agents can serve as a strategic sounding board by simulating scenarios to inform strategy.Essentially, AI agents offer a "virtual team member" who works 24/7, doesn’t get tired, and is intimately familiar with the product and its ecosystem.https://www.chatprd.ai/resources/capabilities-of-ai-agents-product-management2025-03-0721 min
Code ConversationsWhat will AI product management agents do for us?AI is transforming product management workflows by helping product managers (PMs) handle the large amounts of data and tasks they face. AI tools can assist with synthesis, writing, surfacing insights, and providing creative suggestions, without replacing the intuition, empathy, and influence that PMs bring. These tools can help with tasks like PRD (Product Requirements Document) writing and user research. AI helps manage the complexity and volume of information in real-time. Tools like ChatPRD can help product managers work smarter and faster. The right AI tools can free product managers to focus on strategic and creative aspects of their role...2025-03-0417 min
Code ConversationsFuture Potential of AI-Driven Product ManagementAI has the potential to transform product management workflows and responsibilities in several significant ways. Looking ahead, AI could change how product managers operate. If today's AI assistants respond to prompts and automate basic tasks, the future may bring more proactive and intelligent AI agents.Here are some of the most significant potential transformations: Proactive strategy and decision support: Future AI agents may continuously analyze a product’s ecosystem and proactively recommend strategic moves. For example, an AI agent might suggest shifting focus to a rapidly growing user segment or developing tailored features. They could also mo...2025-02-2815 min
Code ConversationsUsing AI to write a product requirements documentHere's a description for a post about using AI to write a product requirements document (PRD), based on the provided source:Are you a product manager looking to streamline your PRD writing process? Discover how AI tools like ChatPRD can help you draft, refine, and update PRDs more efficiently. AI can automate repetitive tasks, provide instant feedback, and ensure consistency, ultimately saving you time and optimizing resources.Key benefits of using AI for PRD development include:Increased efficiencyEnhanced consistencyError reductionData-driven insightsResource optimizationWith AI tools, you can focus on strategic...2025-02-2513 min
Code ConversationsProduct Management in the Age of AIThe article "Product Management Is Dead" argues that artificial intelligence (AI) is rapidly changing the product management landscape. AI is automating many previously manual tasks, such as strategy definition and document creation, leading to a decentralized and accelerated workflow. The author suggests that successful product managers will need to adapt by automating tasks, expanding their skill sets (e.g., coding, data analytics), and teaching their teams to utilize AI effectively. This shift necessitates a move towards generalist specialists who can handle multiple aspects of product development, rather than traditional siloed roles. The article concludes that embracing AI is crucial for pr...2025-02-2108 min
Code ConversationsGoogle's AI Prompt Engineering Course SummaryThe YouTube video summarizes Google's prompt engineering course, emphasizing a five-step framework for effective prompt design: task, context, references, evaluate, and iterate.
This framework can be remembered using the mnemonic "Tiny crabs ride enormous iguanas". The course also covers four methods for iterating on prompts, which include revisiting the prompting framework, simplifying the prompt, trying different phrasing, and introducing constraints.
The course also explores multimodal prompting using various inputs like text, images, and audio, and introduces advanced techniques such as prompt chaining, Chain of Thought prompting, and Tree of Thought prompting.
Furthermore, it...2025-02-1828 min
Code ConversationsLean Team Topologies for Amplified ProductivityCustomer Value, Customer Centricity, Product Success are some of the ultimate goals of an organisation.
And to achieve them one of the focus area for an organisation is to ensure that the teams are setup and interacting efficiently to deliver customer value with speed.
In this session, we will discuss how to define an efficient team topology for teams to deliver customer value. we will go through some of the lessons and learnings I had while implementing the Team Topologies principles and practices developed by Matthew Skelton and Manuel Paisin which helped the organisation to be more focused on...2025-02-1417 min
Code Conversations9 DevOps Team PatternsIt seems that in our industry, many don’t know what to do with DevOps teams. QA team, we know about them. Software engineering teams, we know where to put them. But DevOps? There is a big gap between the leaders and how companies really practice it, like putting it as another team between Dev and Ops. In this video and the previous one, we demystified DevOps teams topologies. For the second video, lets talk about 9 correct ways of having the right topology.
2025-02-1023 min
Code ConversationsTeam Topologies with Matthew SkeltonMatthew Skelton, Founder at Conflux and co-author of Team Topologies, joins the community to discuss Untangling software delivery with Team Topologies, flow metrics, and careful decoupling
The key predictive IT delivery metrics uncovered by the book Accelerate and the State of DevOps Reports - aka “DORA metrics” - point the way towards flow-centric operating models for every modern enterprise building and running software-enriched services. However, improving flow of value within an organization is often difficult due to cross-team dependencies and coupling: everything is tangled. In an organization with 700 software engineers, if 60% of the time is spent waiting on other team...2025-02-0616 min
Code ConversationsPlatform as a Product - Why Platform as a Product?This video is a free preview from the 2h course "Platform as a Product" available on the Team Topologies Academy: https://bit.ly/3o5aLmt
2025-02-0306 min
Code ConversationsA Team-Centric Approach: Kubernetes as Foundation, Not PlatformManuel Pais discusses how many organizations see Kubernetes as “the” platform, rather than just a technical foundation for a true internal platform. Successful Kubernetes adoption requires thinking about what a platform really means and learning which team structures and interactions work well. And evolve them over time.
https://www.youtube.com/watch?v=Iu_T3X-bPqE2025-01-3021 min
Code ConversationsDesigning Teams for Modern Software SystemsRecent research summarised in the book Accelerate points to a set of practices that lead to high software development organisation performance. Simultaneously, research from the Santa Fe institute on Complex Adaptive Systems over the last 20 years seems to point to a grand unified theory of organisational design. So have we cracked it? Do we now have the answer to the question: how do we create and scale high performing software and organisations?
In this talk, James explores the relationships between team structure, software architecture and the emergent phenomenon of complexity science.
https://www.youtube...2025-01-2319 min
Code ConversationsTeam Topologies: Thinnest Viable Platform (TVP)Matthew Skelton and Manuel Pais - co-authors of the book Team Topologies - discuss the concept of a Thinnest Viable Platform (TVP) and what this means for organizations building and running modern software systems.
2025-01-2003 min
Code ConversationsPlatform as a Product: Fundamentals and Best PracticesSavvy organisations are discovering the value of treating their internal platforms as products. But what does it mean to treat a “platform as a product”? What benefits does this give, and why would an organisation adopt this approach?
In this talk, Manuel Pais, co-author of the book Team Topologies, explains why the platform-as-product approach can be a game-changer for organisations building and running software-enabled products and services. Using ideas & patterns from Team Topologies - including Thinnest Viable Platform, team cognitive load, and the evolutionary team interaction modes - Manuel explains how organisations like Adidas and Uswitch have successfully used the...2025-01-1623 min
Code ConversationsTeam Topologies, Cognitive Load & Complex SystemsThe "Engineering Room" is a monthly series of conversations with people who are influential in the software industry. In this episode Dave Farley, author of "Continuous Delivery", "Modern Software Engineering" and others, talks to Matthew Skelton co-author of one of the most significant software books of the last 10 years - “Team Topologies”, about the ingredients for long-term, viable, sustainable and understandable software development.
Matthew Skelton is co-author of "Team Topologies: organizing business and technology teams for fast flow". He is Head of Consulting at Conflux and specialises in Continuous Delivery, operability, and organisation dynamics for modern software systems.
In this...2025-01-1324 min
Code ConversationsBuilding Successful Platform TeamsWhat is a platform team, and how do you build effective platforms? Platforms are often an important part of the strategy to scale software development beyond small single teams. Dividing work up so that common behaviours and services can be shared, rather than every service team implementing their own version, is a big gain, but it can also be a big cost. Coupling between teams is one of the biggest causes of problems when trying to build software on larger scales.
In this episode, Dave Farley, author of "Continuous Delivery" and “Modern Software Engineering” describes the pitfalls common to plat...2025-01-0911 min
Code ConversationsTeam TopologiesMatthew and Manuel's excellent book Team Topologies described the challenges and proposed patterns for organizing teams effectively.
We'll explore their ideas, what patterns are working, and how they might look on Flight Level 2 and 3.
https://www.youtube.com/watch?v=ckGjOkMTGKo2025-01-0618 min
Code ConversationsWhat are AI Agents?AI agents are a type of compound AI system that uses a large language model (LLM) to control its logic. Compound AI systems combine models and other components to solve problems, and they are more adaptable and effective than models alone.
Here are some key points about AI agents from the sources:
Compound AI Systems: These systems combine different components, including models, programmatic elements, and tools, to solve complex tasks. They are modular and can be adapted more quickly than monolithic models.
Control Logic: The path that a program takes to answer a query is known...2025-01-0415 min
Code ConversationsScaling AI Model Training and Inferencing Efficiently with PyTorchhttps://youtu.be/85RfazjDPwA?si=TM2RugT9QEd1UOZj
Comprehensive Overview of PyTorch Tools for Scaling AI Models
Scaling AI models often involves adding more layers to neural networks to enhance their ability to capture data nuances and execute complex tasks. However, this scaling process demands increased memory and computational power. To address these challenges, PyTorch offers tools like Distributed Data Parallel (DDP) that distribute the training workload across multiple GPUs, enabling faster model training.
Distributed Data Parallel (DDP) comprises three key steps:
Forward Pass: Data is passed through...2024-12-3125 min
Code ConversationsWhat is PyTorch_ (Machine_Deep Learning)https://youtu.be/fJ40w_2h8kk?si=YILy9Od6YICopdFf
PyTorch is an open-source framework that simplifies the process of building, training, and deploying machine learning and deep learning models. The "Py" signifies its integration with the popular Python programming language, making it easily accessible to the vast community of data scientists who favor Python.
PyTorch streamlines the entire model development workflow.
PyTorch's flexibility is a major advantage. It can be run on various hardware, from standard CPUs to powerful GPUs, and even on mobile devices. This adaptability allows you to scale your projects as needed, whether...2024-12-2720 min
Code ConversationsWhat is Back Propagation
Back propagation is an algorithm that modifies the weights and biases of a neural network to reduce error and improve accuracy. The goal of back propagation is to minimize the difference between the network's output and the desired output. This is an iterative process that continues until the network can reliably produce the desired output.
Neural networks consist of layers of interconnected neurons, including an input layer, hidden layers, and an output layer. Forward propagation occurs when data is passed through the network from the input layer to the output layer. During forward propagation...2024-12-2414 min
Code ConversationsLarge Language Models Are Zero Shot Reasoners
Zero-shot prompting asks a question without giving the LLM any other information. It can be unreliable because a word might have multiple meanings. For example, if you ask an LLM to "explain the different types of banks" it might tell you about river banks.
Few-shot prompting gives the LLM an example or two before asking the question. This gives the LLM more context so it can give you a better answer. It can also help the LLM understand what format you want the answer in.
Chain-of-thought prompting asks the LLM to explain how it got its answer...2024-12-2014 min
Code ConversationsSupervised vs. Unsupervised LearningSupervised learning uses labeled data, like a student learning with a teacher. Unsupervised learning uses unlabeled data and is more like self-study.
Supervised learning knows the right answers in advance and aims for accuracy. It can classify data, like filtering spam, or predict values, like stock prices.
Unsupervised learning finds hidden patterns on its own. Think about grouping similar customers or discovering what products are often purchased together.
Semi-supervised learning combines both approaches, using a bit of labeled data to guide the learning from a larger set of unlabeled data. This can be...2024-12-1718 min
Code ConversationsUse AI-Powered Automation to Accelerate Auto Claims ProcessingInsurance companies can reduce the stress of car accidents for their customers by using AI to streamline the claims process. Using AI, an insurance company can set up an automated claims processing workflow so customers can provide basic information to begin the claims process immediately after an accident. Customers can also use their smartphones to gather information about the other party, document damage to their vehicles, and select their preferred auto repair shop. Insurance companies can also arrange for a ride-sharing service to pick up the customer after the accident. All of these features, enabled by a hybrid cloud...2024-12-1304 min
Code ConversationsWhat is an RBM?A Restricted Boltzmann Machine (RBM) is a probabilistic graphical model used for unsupervised learning. RBMs help discover hidden structures in data, making them suitable for applications like video recommendation systems.
An RBM consists of two layers:
Visible Layer: This layer receives the input data.
Hidden Layer: This layer represents features or classifications derived from the input data.
Every node in the visible layer connects to every node in the hidden layer, but there are no connections within the same layer. This characteristic makes it "restricted." The connections have weights representing the probability of nodes being...2024-12-1012 min
Code ConversationsWhat is a Knowledge Graph?Knowledge graphs are a powerful tool for organizing and understanding information. They consist of nodes, which represent entities such as people, places, or things, and edges, which represent relationships between those entities. Knowledge graphs can be used to answer questions, make predictions, and find connections between seemingly unrelated information. For example, they can help identify patterns in data from different sources, such as online reviews and census data, to infer facts that might not be immediately obvious. They also play a significant role in various applications, including virtual assistants, recommendation systems, and fraud detection.
htt...2024-12-0613 min
Code ConversationsWhat is Random Forest?Random Forest is a machine learning model used for making predictions. It uses a collection of decision trees, each trained on a random subset of data, to enhance prediction accuracy.
Decision trees are a simpler type of model that use a series of decisions to classify data. They are susceptible to problems like bias and overfitting.
Imagine deciding whether to play golf. A decision tree might consider factors like time, weather, and availability of clubs.
Overfitting occurs when a model memorizes the training data instead of generalizing from it. This makes the model...2024-12-0320 min
Code ConversationsWhat is NLP (Natural Language Processing)?Natural language processing (NLP) is a field of artificial intelligence that enables computers to understand and process human language. This video from IBM Technology explains the basics of NLP by comparing human language to a computer's understanding. The video describes how NLP uses various techniques to translate unstructured text into structured data that computers can understand. It then highlights several real-world applications of NLP, including machine translation, virtual assistants, sentiment analysis, and spam detection. Finally, the video explores some key NLP techniques, such as tokenization, stemming, lemmatization, part-of-speech tagging, and named entity recognition.
https://y...2024-11-3016 min
Code ConversationsWhat are GANs (Generative Adversarial Networks)?Generative Adversarial Networks (GANs) are a type of unsupervised machine learning algorithm where two submodels, a generator and a discriminator, compete against each other. The generator creates fake samples, while the discriminator attempts to distinguish between real samples from a domain and fake samples from the generator. The adversarial nature of GANs lies in this competition. The generator iteratively creates samples, updating its model until it can generate samples convincing enough to fool both the discriminator and humans. Both the generator and discriminator receive feedback on their performance, and the loser updates its model accordingly. This process continues until...2024-11-2609 min
Code ConversationsWhat are Convolutional Neural Networks (CNNs)?The source is a video from IBM Technology on YouTube that explains the concept of convolutional neural networks (CNNs) in an easy-to-understand manner. The video uses a simple house drawing as an example to illustrate how CNNs, through the use of filters, can identify patterns and perform object recognition. It emphasizes that CNNs are a specialized area of deep learning, consisting of multiple interconnected layers with filters that recognize patterns. The video further discusses how CNNs have numerous real-world applications in fields like optical character recognition, visual search, medical imaging, and more.
https://youtu.be/QzY57FaENXg...2024-11-2209 min
Code ConversationsWhy Are There So Many Foundation Models?The provided text explains the growing prevalence of foundation models in artificial intelligence. These models are large-scale neural networks trained on massive datasets, enabling them to perform various tasks through transfer learning. The text highlights the NASA Geospatial Model, developed in collaboration with IBM, which uses satellite imagery to predict climate-related events like floods and wildfires. This model serves as an example of how foundation models can be fine-tuned to address specific needs and applications across diverse fields, thus contributing to the proliferation of such models.
https://youtu.be/QPQy7jUpmyA?si=l1hKaYHyUFgMmKiR2024-11-2011 min
Code ConversationsFive Steps to Create a New AI ModelThe video transcript from IBM Technology describes a five-stage workflow for creating specialized AI models using foundation models. The workflow begins with data preparation, where large datasets are curated, categorized, and filtered. Next, the data is used to train a foundation model, which is a pre-trained model that can be adapted for various purposes. After training, the model is validated using benchmark tests to assess its performance. The model can then be tuned by application developers using additional data, improving its performance for specific tasks. Finally, the tuned model is deployed as a service or embedded into an application. The video...2024-11-1614 min
Code ConversationsIntro to Large Language ModelsThis excerpt from Andrej Karpathy's YouTube video, "[1hr Talk] Intro to Large Language Models," provides a comprehensive overview of large language models (LLMs), delving into their core components, training process, capabilities, and future directions. The video highlights the fundamental concept of LLMs as "zip files" of the internet, where massive amounts of text data are compressed into neural network parameters. It explains the two crucial stages of training: pre-training, where models learn to predict the next word in a sequence, and fine-tuning, which aligns these models for specific tasks, like answering questions or generating text in a helpful assistant...2024-11-1330 min
Code ConversationsLarge Language Models (LLMs) - Everything You NEED To KnowA brief introduction to everything you need to know about Large Language Models (LLMs) to go from knowing nothing to having a solid foundation of understanding to take your learning to the next level. Special thank you to the students at AI Camp who helped craft this video!
Matthew Berman
https://www.youtube.com/watch?v=osKyvYJ3PRM2024-11-1017 min
Code ConversationsWhat are Large Language Models (LLMs)?Learn about Large Language Models (LLMs), a powerful neural network that enables computers to process and generate language better than ever before. Dale and Nikita share how LLMs work and how you can interact with them via prompts.
by Google for Developers
https://www.youtube.com/watch?v=iR2O2GPbB0E2024-11-0718 min
Code ConversationsIntroduction to large language modelsLarge Language Models (LLMs) and Generative AI intersect and they are both part of deep learning. Watch this video to learn about LLMs, including use cases, Prompt Tuning, and GenAI development tools.
By Google Cloud Tech
https://www.youtube.com/watch?v=zizonToFXDs2024-11-0313 min
Code ConversationsHow Event Driven Architectures Go Wrong & How to Fix ThemThis is an excerpt from a talk at the GOTO 2024 conference about how event-driven architectures can go wrong. The speaker, Matthew Meckes, first establishes the goals of event-driven architectures, which include scalability, agility, and fast feedback loops. Then, he introduces a series of anti-patterns, or common mistakes, that developers often encounter when building these architectures. These patterns, often characterized by a lack of communication and a reliance on "YOLO" (You Only Live Once) practices, can lead to significant technical debt and hinder the desired benefits of event-driven architectures. Meckes ultimately argues that the solution to these problems lies in...2024-10-2914 min
Code ConversationsEvent-Driven Architecture by Martin FowlerMartin Fowler, a renowned software developer, discusses the various interpretations of event-driven architecture. He identifies four common patterns that often fall under this umbrella: event notification, event carried state transfer, event sourcing, and command query responsibility segregation (CQRS). Fowler delves into the benefits and drawbacks of each pattern, emphasizing the importance of understanding their specific characteristics and potential trade-offs. He uses examples from everyday software development and business practices to illustrate these concepts, ultimately advocating for a more precise understanding of the various forms of event-driven architecture to improve communication and facilitate better decision-making.
2024-10-2209 min
Code ConversationsDarkside of Event-Driven ArchitectureEvent-Driven Architecture has a lot of benefits but comes at a cost of another set of problems. Visibility into workflows and business processes, consistency, idempotency, and consumer lag to name a few.
2024-10-1912 min
Code ConversationsA Beginner's Guide to Event-Driven ArchitectureIn this gentle introduction to Event-Driven Architecture, we will explore real-world use cases and main concepts such as Event Notification, CQRS, Event Sourcing, etc. We'll discuss common technologies and patterns, such as Messaging with RabbitMQ and Streaming with Kafka.2024-10-1512 min
Code ConversationsEvent Driven Architecture by Dave FarleyThis video explores the fundamentals of event-driven architecture (EDA), highlighting its increasing popularity, particularly for larger and more complex systems. The video contrasts EDA with traditional command-oriented programming and emphasizes its benefits in decoupling code, promoting separation of concerns, and enhancing system scalability and resilience. The speaker provides practical advice for implementing EDA, advocating for modeling events based on real-world business logic and illustrating how this approach facilitates incremental system growth and adaptation. The video also introduces concepts like event storming and domain-driven design, which can be used to design systems that are more robust and adaptable.2024-10-1208 min
Code ConversationsEvent-Driven ArchitectureThe video from the YouTube channel "Alex Hyett" explores the concept of event-driven architecture in the context of microservices. The video highlights the benefits of event-driven architecture over traditional API-driven models, emphasizing its ability to decouple components, improve scalability, and facilitate dependency inversion. However, the video also acknowledges potential drawbacks such as the possibility of data inconsistency and the need for item potency in handling duplicate events. The video concludes by emphasizing the importance of considering the complexity and overhead associated with event-driven architecture before adopting it, suggesting it might not be the optimal choice for systems that don't re...2024-10-0606 min
Code ConversationsEvent-Driven Architecture vs Request-Response ArchitectureWe deep dive in the differences between two architectural approaches used for building applications: event-driven architecture (EDA) and request/response architecture (RR).
2024-10-0309 min