In this episode of Generative AI 101, we discover the origins and workings of the Elo Rating System—a clever, adaptable method originally designed to rank chess players but now influencing everything from online gaming to, most importantly for us, AI models. We’ll explore how this simple yet effective system predicts match outcomes, adjusts rankings, and even finds parallels in areas like online dating. Whether you’re a game developer, an AI enthusiast, or just curious about how algorithms shape...
Sep 04, 2024•8 min•Ep. 45
In this episode of Generative AI 101, we’re exploring the need-to-know LMSYS Org and their innovative Chatbot Arena. LMSYS Org, a collaboration between top minds at UC Berkeley, UC San Diego, and Carnegie Melon University, is breaking new ground by making powerful AI models accessible to everyone. They’re not just creating AI—they’re building a community where anyone can contribute and evaluate top LLMs. We also explore the Chatbot Arena, where AI models face off in real-time, with human users l...
Sep 03, 2024•6 min•Ep. 44
In this episode of Generative AI 101, we explore evaluating Generative AI large language models (LLMs). Just like finding the best restaurant in town means more than judging a single dish, evaluating AI models requires a comprehensive approach. We break down why assessing performance, comparing models, and building user trust are central to evaluation. From authenticity to speed, and fairness to cost, we cover the key factors that determine an AI's true potential. Connect with Us: If you enjoyed...
Sep 02, 2024•8 min•Ep. 43
In this episode of Generative AI 101, we’re tackling the curious case of AI hallucinations—when AI creates content that’s completely off the mark. We’ll explore how these digital daydreams happen, why humans aren’t immune to similar slip-ups, and the impact these hallucinations can have. Whether amusing or alarming, AI hallucinations are a phenomenon you’ll want to understand. Check out this Paper: WildHallucinations: Evaluating Long-form Factuality in LLMs with Real-World Entity Queries Connect...
Aug 28, 2024•6 min•Ep. 42
In this episode of Generative AI 101, we’re fine-tuning your AI prompting skills. Learn how to refine prompts to turn mediocre responses into top-tier results. We’ll cover techniques like iterative prompting, using context, and applying constraints, along with ethical considerations to ensure fairness. Get ready to make your AI work smarter, not harder. Connect with Us: If you enjoyed this episode or have questions, reach out to Emily Laird on LinkedIn . Stay tuned for more insights into the evo...
Aug 27, 2024•9 min•Ep. 41
In this episode of Generative AI 101, we’re exploring the various flavors of generative AI bias and inaccuracy—those pesky issues that make your AI sound like it’s stuck in a 1950s sitcom. From data-driven biases baked into AI’s training to sneaky algorithmic quirks and the all-too-human flaws we project onto our creations, we explore how to recognize and mitigate these pitfalls. Learn how strategic prompting can tone down clichés and overgeneralizations, making your AI smarter and fairer. Plus,...
Aug 26, 2024•7 min•Ep. 40
In this episode of Generative AI 101 , we catch a wave into the BAB framework (we're totally calling it "BABE")—an effortlessly cool method for crafting AI prompts that turn "meh" into "tubular!" BAB, short for Before, After, and Bridge, guides you from dull, lifeless AI interactions to responses that shine like a pro surfer catching the perfect wave. Learn how to structure your prompts for clarity, precision, and maximum impact, ensuring your AI delivers every time. If you enjoyed this episode ...
Aug 21, 2024•5 min•Ep. 39
In this episode of Generative AI 101 , we explore CARE Prompting—a sophisticated method that prioritizes Craft, Audience, Response, and Evaluation to fine-tune AI outputs. CARE Prompting is designed to create responses that go beyond accuracy, ensuring they resonate deeply and reflect a comprehensive understanding of your goals. If you enjoyed this episode or have questions, reach out to Emily Laird on LinkedIn . Stay tuned for more insights into the evolving world of AI and prompt engineering. ...
Aug 20, 2024•7 min•Ep. 38
In this episode of Generative AI 101 , we’re taking a high-speed tour of the RACE Prompting method—where Role, Audience, Context, and Example aren’t just pit stops, but the keys to better communication. Ready to take your AI skills to the next lap? Connect with Emily Laird on LinkedIn. Stay tuned for more laps around the ever-evolving circuit of AI and prompt engineering. Connect with Emily Laird on LinkedIn...
Aug 19, 2024•5 min•Ep. 37
In this episode of Generative AI 101, we explore the ins and outs of RTF Prompting—an approach that sharpens your AI's focus by defining its Role, Task, and Format. Whether you're tasking your AI with writing a travel blog, analyzing financial data, or extracting historical records, RTF Prompting provides the clarity and structure needed to achieve precise results. We’ll break down how to use this versatile tool, discuss its pros and cons, and share some entertaining examples that highlight its ...
Aug 14, 2024•8 min•Ep. 36
In this episode of Generative AI 101, we break down the concept of self-consistency prompting—a technique that enhances AI accuracy by posing the same question in multiple ways and selecting the most consistent answer. By guiding your large language model through varied prompts, this method improves performance on complex reasoning tasks and reduces errors. However, it's not without challenges: it demands more computational power and isn't entirely foolproof. Self-Consistency Prompting paper Con...
Aug 13, 2024•8 min•Ep. 35
In this episode of Generative AI 101 , we break down the concept of chain-of-thought prompting—a technique that helps AI models think through complex tasks step by step, improving their logical and accurate responses. By guiding the AI, or your large language model of choice, through detailed instructions, this method enhances performance on tasks like arithmetic and decision-making. However, it’s not without challenges: it works best with large models and can be resource-intensive. Connect with...
Aug 12, 2024•6 min•Ep. 34
In this episode of Generative AI 101, we explore the example-heavy world of few shot prompting. Imagine describing a dish you love to a chef and then offering them multiple recipes on how to make it. That's few-shot prompting—maximum input, maximum efficiency. We'll explore how this technique can turn your AI into a translation whiz or a sentiment analysis expert with just one example. We'll also discuss the pros and cons of this approach. Connect with Emily Laird on LinkedIn...
Aug 07, 2024•8 min•Ep. 33
In this episode of Generative AI 101, we dive into the art of one-shot prompting. Imagine teaching someone a recipe with just one perfect example instead of a whole cookbook. That's one-shot prompting—minimal input, maximum efficiency. We'll explore how this technique can turn your AI into a translation whiz or a sentiment analysis expert with just one example. We'll also discuss the pros and cons of this approach, compare it with zero-shot prompting, and share vivid real-world scenarios. Tune i...
Aug 06, 2024•6 min•Ep. 32
Join us on Generative AI 101 as we demystify zero-shot prompting—a technique that lets LLMs perform tasks without prior examples. Imagine whipping up a dish you've never heard of with no recipe; that's zero-shot prompting in action. We’ll explore how AI models leverage vast pre-existing knowledge to answer questions, classify sentiments, and more, all without specific training. But it's not all smooth sailing; we'll also discuss quirks like the "Reversal Curse," where LLMs struggle with reversed...
Aug 05, 2024•7 min•Ep. 31
In this episode of Generative AI 101, we continue with the art of crafting the perfect prompt for AI. Much like brewing the perfect cup of coffee, the right balance of persona, output format, context, examples, and instructions can transform a bland response into a rich, engaging answer. Tune in as Emily breaks down these five key elements, provides real-world examples, and shares tips to elevate your prompt engineering skills from average to exceptional. Connect with Emily Laird on LinkedIn...
Jul 31, 2024•8 min•Ep. 30
In this episode of Generative AI 101, we uncover the art of crafting perfect prompts for AI. Think of it as giving precise instructions to a master chef. We'll break down the anatomy of a prompt into three key components: instructions, context, and constraints. By comparing effective and ineffective examples, we show you how to transform vague requests into specific, actionable prompts. From enhancing customer support interactions to generating insightful data reports, you'll learn how well-stru...
Jul 30, 2024•8 min•Ep. 29
In this episode of Generative AI 101, we dig into the world of prompt engineering. Think of it as giving your AI precise instructions, like ordering the perfect Starbucks beverage. We’ll explore how writing effective prompts can turn an AI into a super-smart assistant, capable of generating compelling text, aiding customer support, and analyzing large amounts of data. From overcoming writer’s block to handling customer queries efficiently, prompt engineering is the unsung hero that maximizes AI ...
Jul 29, 2024•7 min•Ep. 28
Join us as we explore the world of Meta's LLaMA in this episode of Generative AI 101. From its origins in 2013 with Facebook AI Research (FAIR), led by AI visionary Yann LeCun, to the groundbreaking release of LLaMA models in 2023, we'll explore how Meta has pushed the boundaries of AI. Discover the evolution from the initial LLaMA leak that took the AI world by storm to the refined, ethically-designed LLaMA 2, and finally, the powerful and efficient LLaMA 3 released in 2024. Tune in to understa...
Jul 24, 2024•7 min•Ep. 27
Get ready to meet Microsoft Copilot, the AI assistant that's redefining productivity. Launched in February 2023, Copilot evolved from Bing Chat to become a versatile tool embedded in Microsoft 365. Powered by OpenAI’s GPT-4 and the Microsoft Prometheus model, Copilot excels at everything from drafting emails and analyzing data to creating stunning PowerPoint presentations. Despite its initial quirks, Copilot has become an indispensable ally in the digital workspace, thanks to Microsoft’s hefty i...
Jul 23, 2024•7 min•Ep. 26
Bonjour, tech-savvy wanderers! In this episode of Generative AI 101, we're diving fork-first into Mistral AI, the French powerhouse in the world of artificial intelligence. Founded by ex-Google DeepMind and Meta researchers, Mistral AI offers cutting-edge models that are shaking up the industry. From the versatile Mistral Large and Small to the sharp Mistral Embed and open-source Mistral 7B, these models are giving giants like GPT-4 a run for their money. We'll also explore their Mixtral series,...
Jul 22, 2024•9 min•Ep. 25
In this episode of Generative AI 101, we explore the world of Anthropic's Claude AI—a chatbot born from the minds of ex-OpenAI siblings and backed by tech giants like Google and Amazon. Picture Claude as the cool, thoughtful cousin of ChatGPT, capable of handling 200,000 tokens at once. With the latest iteration, Claude 3.5 Sonnet, this AI sets new benchmarks in graduate-level reasoning, broad knowledge, and coding proficiency. Whether you need an advanced model for automation or a speed demon f...
Jul 17, 2024•7 min•Ep. 24
In this episode of Generative AI 101, we explore the slick, high-octane world of Google's Gemini. Think of it as the James Bond of AI—sharp, sophisticated, and always ahead of the curve. We’ll dish out the inside scoop on Gemini’s cutting-edge tech, from its inception to its rise as a superstar in the AI universe. Get ready to explore its suave capabilities, from powering chatty virtual assistants to mastering the nuances of human language and crunching mountains of data like it’s nothing. Plus,...
Jul 16, 2024•5 min•Ep. 23
In this episode of Generative AI 101, we explore the modern marvel that is ChatGPT. Discover what "GPT" stands for and how this "Generative Pre-trained Transformer" operates, processing text like a high-powered engine. Learn what ChatGPT can do, from generating human-like responses to engaging in multi-language conversations and analyzing vast text data. Tune in to explore the incredible capabilities and the global impact of ChatGPT. Connect with Emily Laird on LinkedIn...
Jul 15, 2024•7 min•Ep. 22
In this episode of Generative AI 101, go on an insider’s tour of a large language model (LLM). Discover how each component, from the transformer architecture and positional encoding to the multi-head attention layers and feed-forward neural networks, contributes to creating intelligent, coherent text. We’ll explore tokenization and resource management techniques like mixed-precision training and model parallelism. Join us for a fascinating look at the complex, finely-tuned process that powers mo...
Jul 10, 2024•6 min•Ep. 21
In this episode of Generative AI 101, we explore the intricate process of training Large Language Models (LLMs). Imagine training a brilliant student with the entire internet as their textbook—books, academic papers, Wikipedia, social media posts, and code repositories. We’ll cover the stages of data collection, cleaning, and tokenization. Learn how transformers, with their self-attention mechanisms, help these models understand and generate coherent text. Discover the training process using pow...
Jul 09, 2024•5 min•Ep. 20
In this episode of Generative AI 101, we trace the evolution of Large Language Models (LLMs) from their early, simplistic beginnings to the sophisticated powerhouses they are today. Starting with basic models that struggled with coherence, we'll see how the introduction of transformers in 2017 revolutionized the field. Discover how models like GPT-2 and GPT-3 brought human-like text generation to new heights, and learn about the advancements in GPT-4, which offers even greater accuracy and versa...
Jul 08, 2024•5 min•Ep. 19
In this episode of Generative AI 101, we explore Large Language Models (LLMs) and their significance. Imagine chatting with an AI that feels almost human—you're likely interacting with an LLM. These models, trained on massive datasets, understand and generate text with impressive accuracy. With billions of parameters, they handle a wide range of tasks from chatbots and virtual assistants to sentiment analysis and document summarization. Connect with Emily Laird on LinkedIn...
Jul 03, 2024•4 min•Ep. 18
In this episode of Generative AI 101, we explore the core techniques and methods in Natural Language Processing (NLP). Starting with rule-based approaches that rely on handcrafted rules, we move to statistical models that learn patterns from vast amounts of data. We'll explain n-gram models and their limitations before diving into the revolution brought by machine learning, where algorithms like Support Vector Machines (SVMs) and decision trees learn from annotated datasets. Finally, we arrive a...
Jul 02, 2024•5 min•Ep. 17
In this episode of Generative AI 101, we break down the fundamental concepts of Natural Language Processing (NLP). Imagine trying to read a book that's one long, unbroken string of text—impossible, right? That’s where tokenization comes in, breaking text into manageable chunks. We’ll also cover stemming and lemmatization, techniques for reducing words to their root forms, and explain the importance of stop words—the linguistic background noise. Finally, we’ll explore Named Entity Recognition (NE...
Jul 01, 2024•5 min•Ep. 16
