by Mark and Allen
Mark and Allen talk about the latest news in the VoiceFirst world from a developer point of view.
Language
🇺🇲
Publishing Since
8/1/2020
Email Addresses
1 available
Phone Numbers
0 available
April 3, 2025
<p>Following up on last week's captivating discussion, Allen Firstenberg and Noble Ackerson dive deeper into the world of Generative UI. Explore real-world examples of its potential pitfalls and discover how Noble is tackling these challenges through innovative approaches.</p><p><br /></p><p>This episode unveils the power of dynamically adapting user interfaces based on preferences and intent, ultimately aiming for outcome-focused experiences that seamlessly guide users to their goals. Inspired by the insightful quotes from Arthur C. Clarke ("Any sufficiently advanced technology is indistinguishable from magic") and Larry Niven ("Any sufficiently advanced magic is indistinguishable from technology"), we explore how fine-tuning Large Language Models (LLMs) can bridge this gap.</p><p><br /></p><p>Noble shares a practical demonstration of a smart home dashboard leveraging Generative UI and then delves into the crucial technique of fine-tuning LLMs. Learn why fine-tuning isn't about teaching new knowledge but rather new patterns and vocabulary to better understand domain-specific needs, like rendering accessible and effective visualizations. We demystify the process, discuss essential hyperparameters like learning rate and training epochs, and explore the practicalities of deploying fine-tuned models using tools like Google Cloud Run.</p><p><br /></p><p>Join us for an insightful conversation that blends cutting-edge AI with practical software engineering principles, revealing how seemingly magical user experiences are built with careful technical considerations.</p><p><br /></p><p>Timestamps:</p><p><br /></p><p>0:00:00 Introduction and Recap of Generative UI</p><p>0:03:20 Demonstrating Generative UI Pitfalls with a Smart Home Dashboard</p><p>0:05:15 Dynamic Adaptation and User Intent</p><p>0:11:30 Accessibility and Customization in Generative UI</p><p>0:13:30 Encountering Limitations and the Need for Fine-Tuning</p><p>0:17:50 Introducing Fine-Tuning for LLMs: Adapting Pre-trained Models</p><p>0:19:30 Fine-Tuning for New Patterns and Domain-Specific Understanding</p><p>0:20:50 The Role of Training Data in Supervised Fine-Tuning</p><p>0:23:30 Generalization of Patterns by LLMs</p><p>0:24:20 Exploring Key Fine-Tuning Hyperparameters: Learning Rate and Training Epochs</p><p>0:30:30 Demystifying Supervised Fine-Tuning and its Benefits</p><p>0:33:30 Saving and Hosting Fine-Tuned Models: Hugging Face and Google Cloud Run</p><p>0:36:50 Integrating Fine-Tuned Models into Applications</p><p>0:38:50 The Model is Not the Product: Focus on User Value</p><p>0:39:40 Closing Remarks and Teasing Future Discussions on Monitoring</p><p><br /></p><p>Hashtags:</p><p><br /></p><p>#GenerativeUI #AI #LLM #LargeLanguageModels #FineTuning #MachineLearning #UserInterface #UX #Developers #Programming #SoftwareEngineering #CloudComputing #GoogleCloudRun #GoogleGemini #GoogleGemma #HuggingFace #AIforDevelopers #TechPodcast #TwoVoiceDevs #ArtificialIntelligence #TechMagic</p>
March 28, 2025
<p>Allen and Noble dive deep into the fascinating world of Generative UI, a concept that goes beyond simply using AI to design interfaces and explores the possibility of UIs dynamically generated in real-time by AI LLMs, tailored to individual user needs and context. Noble, a returning Google Developers Expert in AI, clarifies the crucial distinction between generative UI and AI-aided UI generation. They discuss potential applications like dynamic menus and personalized settings, while also tackling the challenges around predictability, usability, and the role of established design patterns. Discover how agents, constrained within defined boundaries, can power this technology and the current limitations when it comes to generating complex UI components. Join the conversation as they explore the cutting edge of how AI could revolutionize the way we interact with software.</p><p><br></p><p>Timestamps:</p><p><br></p><p>00:00:00 - Introduction and Noble's return as a Google Developers Expert in AI</p><p>00:02:00 - Defining Generative UI and distinguishing it from AI-aided design</p><p>00:03:30 - Exploring potential examples of Generative UI based on user needs and context</p><p>00:04:45 - The difference between traditional static UIs and dynamic generative UIs</p><p>00:06:45 - How LLMs can be leveraged for real-time UI generation</p><p>00:07:15 - The overlap and distinction between Generative UI and Conversational</p><p>UI</p><p>00:08:30 - Challenges of Generative UI: Predictability and guiding users</p><p>00:09:30 - The importance of maintaining established UX patterns in Generative UI</p><p>00:12:30 - Traditional UI limitations and the promise of personalized generative UIs</p><p>00:14:00 - Context-specific information access and adapting to user roles</p><p>00:15:30 - An example of Generative UI in a business intelligence dashboard</p><p>00:17:00 - A six-stage pipeline for how Generative UI systems might work</p><p>00:19:00 - The concept of "agents on rails" in the context of UI generation</p><p>00:20:30 - The reasoning and tool-calling aspects of generative UI agents</p><p>00:22:30 - Tools as the core of UI generation and component recognition challenges</p><p>00:24:30 - Demonstrating the dynamic generation of UI components (charts)</p><p>00:27:30 - Exploring interactions and limitations of the generative UI demo</p><p>00:29:15 - The "hallucination" of UI components and the need for fine-tuning</p><p>00:31:30 - Conclusion and future discussion on component fine-tuning</p><p><br></p><p>#GenerativeUI #AI #LLM #UserInterface #UX #AIDesign #DynamicUI #TwoVoiceDevs #GoogleDevelopersExperts #TechPodcast #SoftwareDevelopment #WebDevelopment #AIAgents</p>
March 17, 2025
<p>DeepSeek AI is turning heads, achieving incredible results with older hardware and clever techniques! Join Allen and Roya as they unravel the secrets behind DeepSeek's success, from their unique attention mechanisms to their cost-effective AI training strategies. But is all as it seems? They also tackle the controversies surrounding DeepSeek, including accusations of data plagiarism and concerns about censorship. This episode is a must-listen for anyone interested in the future of AI!</p><p><br></p><p>Timestamps:</p><p><br></p><p>0:00 Why DeepSeek is creating buzz</p><p>1:06 Unveiling DeepSeek's Two Key Models</p><p>2:59 Understanding the Power of Attention</p><p>4:12 What is the latent space?</p><p>5:55 The nail salon example: Multi-Head Attention Explained</p><p>10:02 The doctor/cook/police analogy: Mixture of Experts Explained</p><p>13:51 AI vs. AI: DeepSeek's Cost-Saving Training Method</p><p>16:01 Hallucinations: Is AI Training Too Risky?</p><p>20:59 What are Reasoning Models and Why Do They Matter?</p><p>26:53 LLMs are pattern systems explained</p><p>28:22 How DeepSeek is using old GPUs</p><p>32:53 OpenAI vs. DeepSeek: The Data Plagiarism Debate</p><p>39:32 Political Correctness: The Challenge of Guardrails in AI</p><p>42:16 Why Open Source is Crucial for the Future of AI</p><p>43:20 Run DeepSeek locally on OLAMA</p><p>43:56 Final Thoughts</p><p><br></p><p>Hashtags: #DeepSeek #AI #LLM #Innovation #TechNews #Podcast #ArtificialIntelligence #MachineLearning #Ethics #OpenAI #DataPrivacy #Censorship #TwoVoiceDevs #DeepLearning #ReasoningModel #AIRevolution #ChinaTech</p>
swyx + Alessio
Sam Charrington
Nathaniel Whittemore
Conviction
Erik Torenberg
Tim Ferriss: Bestselling Author, Human Guinea Pig
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at [email protected] for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.