Two Voice Devs

In part two of this insightful conversation, Allen and Sam Witteveen dive deep into the rapidly expanding world of AI models beyond the "big three." They explore the impact of open-weight and Chinese models like DeepSeek, Mistral, and Qwen, discussing their impressive efficiency and coding capabilities. The conversation shifts to the rise of agentic workflows and how tools like Claude Code are fundamentally changing the day-to-day lives of developers.They also tackle the tough questions: Are junior developers being replaced? Is AI just the next level of abstraction in programming? Finally, they cover the enterprise side of AI, from on-premise deployments to the evolving landscape of prompt engineering and observability frameworks like LangChain.Timestamps:[00:00:00] Introduction[00:00:49] Exploring Open Weights and Chinese Models[00:03:41] The Value of "Thinking" Models and Distillation[00:06:41] Running Models Locally[00:08:34] The Shift Towards Agentic Workflows[00:12:17] How AI is Changing the Role of Developers[00:29:04] AI as the Next Level of Abstraction[00:35:00] Best Models for Tool Calling and Coding[00:39:04] On-Premise Models and Enterprise Solutions[00:44:49] The Future of Prompt Engineering and LangChain[00:48:37] Outro and Where to Find SamHashtags:#TwoVoiceDevs #AI #OpenWeights #DeepSeek #Mistral #Qwen #ClaudeCode #Gemini #LangChain #SoftwareEngineering #AgenticAI #MachineLearning

In Part 1 of a two-part series, guest host Sam Witteveen joins Allen to catch up and dive deep into the rapidly evolving world of AI models. Sam shares his fascinating journey from being a successful pop songwriter to becoming a Machine Learning Google Developer Expert (GDE) and running the massive Machine Learning Singapore meetup.The conversation shifts to the latest AI developments, exploring the "Big Three" model builders—Anthropic, OpenAI, and Google. Sam and Allen discuss the frenetic pace of new model releases, changes to the Gemini 3 API, and how developers navigate the trade-offs between intelligence, latency, and cost.Finally, they pull back the curtain on how these models are actually trained today. Discover why models are no longer trying to be "fact machines" and how post-training breakthroughs, code execution sandboxes, and Reinforcement Learning (RL) environments are dramatically improving AI capabilities. Stay tuned for the end of the episode, where they hint at what's coming in Part 2!Timestamps:[00:00:00] Introduction and catching up[00:01:33] Sam's fascinating journey from pop music to machine learning[00:05:23] Running the massive Machine Learning Singapore meetup[00:07:42] Stumbling into YouTube and teaching AI with Google Colab[00:12:38] Analyzing the "Big Three" AI models and rapid release cycles[00:17:52] Gemini 3 API updates, Flash models, and thinking levels[00:22:00] Tool use, knowledge cutoffs, and why LLMs aren't fact machines[00:26:00] How post-training and code sandboxes revolutionized AI[00:32:00] Scaling Reinforcement Learning (RL) environments for design[00:34:04] Structured outputs and the return to predictable rules[00:36:43] Tune in next time for more! And where to find Sam onlineHashtags:#TwoVoiceDevs #AI #MachineLearning #DeepLearning #LLM #GoogleGemini #Gemini #OpenAI #ChatGPT #Anthropic #Claude #ReinforcementLearning #RAG #Developers #SamWitteveen

Allen has been busy! This week, he unveils the new `@langchain/google` package for LangChain JS. This major update consolidates five previous libraries into a single, standardized, and powerful tool for developers working with Gemini and Vertex AI. Allen walks Mark through the motivation behind the change, the focus on backward compatibility, and the exciting new features like simplified multimodal input/output and text-to-speech support. If you're building with Google AI and JavaScript, this is the update you've been waiting for.[00:00:57] The confusion of previous packages[00:02:52] Creating a unified package[00:03:45] Introducing @langchain/google[00:04:35] Backward compatibility[00:06:48] Multimodal inputs[00:07:54] Standardizing output and image generation[00:08:58] Text-to-Speech support[00:11:29] Simplifying parameters and reasoning[00:14:55] Future roadmap#LangChain #Gemini #NanoBanana #TextToSpeech #GoogleAI #JavaScript #TypeScript #VertexAI #OpenSource #AI #WebDevelopment #TwoVoiceDevs

Ever wonder how "Two Voice Devs" goes from a raw recording to a finished episode? In this episode, Allen Firstenberg takes Mark Tucker on a deep dive into his production workflow. They discuss how Descript's text-based editing revolutionized their process, how Allen uses a custom Gemini CLI agent to automate show notes and descriptions, and the technical (and ethical!) journey of creating AI-generated thumbnails using Google's Nano Banana. It's a candid look at how AI can act as a force multiplier for creators while keeping the "human in the loop."[00:00:01] Introduction and Check-in[00:01:27] Behind the Scenes: Why We Use AI[00:03:42] Descript: Text-Based Video Editing[00:05:24] Building a Knowledge Database from Transcripts[00:08:13] Editing Video Like a Document[00:12:34] Exploring Descript's AI[00:13:36] Automating Show Notes with Gemini CLI[00:14:10] The Power of System Instructions (GEMINI.md)[00:19:30] AI Thumbnail Generation with Nano Banana[00:26:10] The Ethics of Synthetic Media and Artistic Style[00:28:40] Keeping the Human in the Loop[00:33:00] Evolution of the Two Voice Devs Workflow#TwoVoiceDevs #PodcastProduction #GeminiAI #Descript #GeminiCLI #NanoBanana #Automation #ContentCreation #Ethics #GenerativeAI #AIWorkflow #PodcastEditing

Mark and Allen dive into the emerging world of Agent Skills, an open standard for extending the capabilities of AI coding assistants like GitHub Copilot, Claude Code, and Gemini CLI. They explore how these skills work, how they compare to the Model Context Protocol (MCP), and walk through creating and installing a custom skill using the `skills` CLI. They also discuss the skills.sh website by Vercel, which acts as a registry and leaderboard for the ecosystem. The conversation touches on the potential for standardization, the current fragmentation in the ecosystem, and critical security considerations for these powerful new tools.More Info:* https://agentskills.io* https://skills.sh* https://cra.mr/mcp-skills-and-agents[00:00:00] Introduction & Context: AI Agents and Tools[00:02:18] Getting Information into Context (Instructions files)[00:06:50] What are Agent Skills? (AgentSkills.io)[00:09:55] Agent Skills vs. MCP Servers[00:16:35] How Skills Work: Progressive Disclosure[00:19:50] Mark's Example: List Global NPM Skill[00:22:56] Installing Skills with skill.sh and the Skills CLI[00:26:55] Demo: Installing on GitHub Copilot[00:30:58] Demo: Installing on Gemini CLI[00:37:37] Discussion: Discovery, Standardization, and Security[00:43:05] Conclusion#AgentSkills #AI #GitHubCopilot #GeminiCLI #CodingAssistants #MCP #ModelContextProtocol #DeveloperTools #TwoVoiceDevs

Allen and Mike discuss Google's new "Personal Intelligence" feature for Gemini. They explore how it connects to your personal data like Photos, Gmail, and Docs to provide context-aware answers. The conversation covers real-world use cases, privacy concerns regarding training data, and the importance of transparency and granular control in AI systems. They also touch on the "blackmail" scenario found in other AI research and what developers can learn from Google's implementation.More Info:* https://blog.google/innovation-and-ai/products/gemini-app/personal-intelligence/[00:00:30] Google's Gemini Personal Intelligence announcement[00:01:48] Connecting personal data sources to Gemini[00:03:45] Google's unique advantage with user data[00:06:40] Real-world use case: Tracking travel history[00:07:30] Potential use case: Combining health data sources[00:09:15] Privacy: Is your data used for training?[00:12:40] The debate: Opting in vs. privacy concerns[00:16:30] AI safety and the "blackmail" scenario[00:18:50] Lessons for developers: Granular permissions and transparency[00:20:30] Verifiability and user trust[00:23:50] Conclusion#Gemini #GoogleAI #PersonalIntelligence #Privacy #MachineLearning #Developer #TechPodcast #AI #TwoVoiceDevs

Allen Firstenberg welcomes back guest host Mike Wolfson, an Android Google Developer Expert, to discuss the shifting landscape of User Experience (UX) in the age of Artificial Intelligence. As we move toward autonomous agents and multimodal interactions—incorporating voice, haptics, and environmental data—the reliance on traditional screens and touch interfaces is set to diminish.Mike shares insights on why "context" is the new "queen," illustrating the challenges of current AI with real-world examples (like his Meta glasses failing to find a decent breakfast burrito). The conversation tackles the critical question: "Who does the agent truly work for?" and explores how developers can avoid "notification fatigue" while ensuring users remain informed and in control. From the "creepy" factor of hyper-personalized data to the "Beverage Butler" concept, this episode dives deep into designing for a future where the best UI might be no UI at all.[00:00:00] Welcome and Introduction[00:01:21] The Evolution of UX: Beyond Touchscreens[00:03:52] The Importance of Context: A Meta Glasses Example[00:06:21] Privacy, Creepiness, and Agent Loyalty[00:08:43] Application Development in an AI World[00:11:34] Avoiding the "Seinfeld Assistant" of Notification Fatigue[00:17:15] Feedback Modalities: Tones vs. Speech[00:19:39] Discoverability of Features in Non-Visual Interfaces[00:23:00] The "Beverage Butler" and Future Outlook#AI #UX #UserExperience #ArtificialIntelligence #AndroidDev #ContextAwareness #VoiceUI #NoUI #TechPodcast #TwoVoiceDevs #GDE #GoogleDeveloperExpert #BeverageButler

In this episode, Mark introduces Allen to Parlant, an open-source framework for building agentic AI. They explore how Parlant differs from other frameworks like LangChain and LangGraph by using concepts like "journeys" for flexible conversation flows and "guidelines" for conditional rule application. Mark walks through the key features, including the ability to define glossaries, tools, and the engine's matching process. They also discuss the recent version 3.1 updates, such as linked journeys and behavior criticality levels. Finally, they dive into "Emcie," Parlant's managed NLP service that utilizes a teacher-student model architecture to optimize performance and cost using Small Language Models (SLMs).[00:00:00] Welcome and Introduction[00:00:43] Introduction to Parlant[00:02:03] Journeys: Flexible Conversation Flows[00:03:36] Guidelines: Conditional Rules[00:06:27] Motivations and Compliance[00:08:44] NLP Services and Providers[00:11:42] The Balance Between Rigid and Loose Conversations[00:18:43] Parlant 3.1 Updates: Linked Journeys and Behavior Levels[00:22:20] Custom Matchers[00:23:14] Emcie: Parlant's Managed NLP Service[00:25:05] Model Tiers: Jackal and Bison[00:26:14] Teacher-Student Architecture and SLMs[00:30:26] Cost and Optimization with Student Models[00:35:19] Conclusion and Wrap-up#Parlant #AI #AgenticAI #LLM #SLM #OpenSource #SoftwareDevelopment #TwoVoiceDevs #Emcie #NLP

Happy New Year! Allen and Mark kick off 2026 by looking back at the whirlwind of AI developments in 2025. From the explosion of agentic frameworks like LangGraph, Google's Agent Development Kit, and the Microsoft Agent Framework to the emergence of protocols like MCP and A2A, it was a year of rapid evolution. They discuss the rise of "vibe coding," the state of voice assistants like Alexa Plus and Gemini, and the challenges of monetization and discovery in a model-centric world.What lies ahead in 2026? The duo shares their big predictions! What do we need on the hardware side? Perhaps something new from Google, Microsoft, OpenAI, Amazon, or someone else? What companies are we rooting for? What's next for agents? Tune in and find out!Timestamps:[00:00:00] Introduction and Happy New Year[00:01:13] Reflecting on a busy 2025: Google's weekly announcements[00:02:05] New terms: MCP (Model Context Protocol) and A2A (Agent-to-Agent)[00:03:52] The shift to Agents and Agentic solutions[00:05:40] Framework evolution: Microsoft Agent Framework and LangGraph[00:07:54] The rise of Coding Assistants and "Vibe Coding"[00:09:25] State of Voice: Alexa Plus and Gemini on smart devices[00:11:15] Smart Glasses and the future of ambient AI[00:12:40] MCP: Challenges with discovery, monetization, and security[00:15:10] Microsoft Foundry and low-code agent building[00:20:25] Live Streaming Models: Video, Audio, and Text[00:22:00] 2026 Predictions: Voice Flow acquisition[00:23:05] Prediction: Moving from Chatbots to Autonomous Agents[00:25:20] Prediction: The role of Small Language Models (SLMs)[00:27:10] Closing thoughts and 2026 outlookHashtags:#AI #GenerativeAI #Agents #AutonomousAgents #MCP #A2A #LangGraph #Gemini #VoiceAssistant #SmartGlasses #VoiceFirst #SLM #VoiceFlow #TwoVoiceDevs #YearInReview #2026Predictions #VibeCoding

Get ready for the ULTIMATE SHOWDOWN of holiday cheer and artificial intelligence! In this SPECIAL HOLIDAY EPISODE, Mark and Allen aren't just exchanging pleasantries—they're exchanging MIND-BENDING REBUS PUZZLES generated by some AI models themselves!It's a battle of wits, a clash of code, and a festive face-off as Microsoft Copilot takes on Google's Gemini (and the famous "Nano Banana Pro") to solve visual riddles that will have you shouting at your screen. Can our hosts decipher the scribbles of silicon brains? Or will the AI stump the humans once and for all?Grab your eggnog, put on your thinking cap, and play along! It's Two Voice Devs like you've never seen (or puzzled) them before! HAPPY HOLIDAYS![00:00:00] Intro: The Rules of Engagement[00:02:48] Puzzle 1: A Nipping Chill[00:03:33] Puzzle 2: Going for Gold[00:07:00] Puzzle 3: Escaping the Cage[00:10:00] Puzzle 4: The Silent Mouse[00:11:00] Puzzle 5: A Knightly Gesture[00:12:15] Puzzle 6: Sweet Ballerina[00:13:30] Puzzle 7: Listen Closely to the Animal[00:15:30] Puzzle 8: A Holiday Wish[00:16:15] Puzzle 9: The Grand Finale Challenge[00:19:30] Happy Holidays from Two Voice Devs!#TwoVoiceDevs #HolidaySpecial #RebusPuzzles #LLMBattle #AIShowdown #Copilot #Gemini #NanoBananaPro #ChatGPT #ArtificialIntelligence #MachineLearning #JackFrost #WinterWonderland #Freeze #SugarPlumFairy #Nutcracker #NewYears #Gnu #MerryChristmas #FestivalOfLights #Hanukkah #Kwanzaa #Unity #HolidayFun #Games #Puzzles #TechHumor #DevLife #HappyHolidays #SeasonsGreetings #Fun #Creative #OverTheTop #Podcast #Developers #SoftwareEngineering

Mark Tucker explores Microsoft Azure's "Voice Live" feature within the newly rebranded Microsoft Foundry. He demonstrates how to take a standard text-based AI agent—in this case, one that talks like a pirate—and instantly give it a voice using WebSockets to bridge speech-to-text and text-to-speech. Mark walks through the differences between the "Old" Foundry (V1) and the "New" Foundry (V2), shows the configuration steps, and dives into a Python code example to connect it all together.Learn more:* https://github.com/rmtuckerphx/voicelive-agents-quickstart[00:00:00] Intro and Holiday Plans[00:00:46] Introducing Microsoft Azure Voice Live[00:02:00] Microsoft Foundry Overview[00:02:46] Creating a Pirate Agent in Foundry[00:04:46] Enabling Voice Live in the Playground[00:07:46] Demo: Speaking with the Pirate Agent[00:08:46] Comparing Old and New Foundry[00:13:46] Code Walkthrough: Voice Live Quick Start[00:15:46] Connecting Version 2 Agents[00:18:46] Conclusion#MicrosoftAzure #VoiceLive #MicrosoftFoundry #AI #VoiceFirst #GenerativeAI #SpeechToText #TextToSpeech #Python #Coding

Allen and Mark discuss the architecture of Model Context Protocol (MCP)servers, using Allen's experience with "Vodo Drive" as a case study.They dive into critical considerations for building effective agents,focusing on security, managing API complexity, and enforcing businesslogic. The conversation explores how to move beyond simple REST APIwrappers to create high-level, context-aware tools that ensure safetyand efficiency.[00:00:00] Welcome and Introduction[00:00:54] Lessons from Vodo Drive for MCP[00:02:54] The Importance of Security in MCP Servers[00:03:36] Managing API Complexity and Business Logic[00:05:58] Authentication and Authorization Challenges[00:07:37] OAuth Scopes and User-Controlled Access[00:10:48] Handling Complex APIs like Google Workspace[00:13:58] Designing High-Level Tools vs. Low-Level wrappers[00:19:35] Dynamic Tool Lists and Context Awareness[00:24:14] Agents Acting On Behalf of Users, Not As Users#MCP #ModelContextProtocol #AI #Agents #VodoDrive #Security #API#GoogleWorkspace #SoftwareArchitecture #TwoVoiceDevs

In this episode of Two Voice Devs, Mark Tucker and Allen Firstenberg dive into the world of GitHub Copilot. Mark shares his recent experience preparing for the GitHub Copilot (GH-300) certification and walks us through the various features and modes of the tool within Visual Studio Code. They discuss the differences between "Ask," "Edit," and "Agent" modes, how Copilot integrates with your workspace and terminal, and the power of using different AI models like Sonnet and Gemini. Whether you're new to AI coding assistants or looking to get more out of your current setup, this episode provides a practical overview of what GitHub Copilot can do today.[00:00:00] Introduction and updates[00:01:26] The GitHub Copilot (GH-300) Certification[00:02:30] GitHub Copilot in Visual Studio Code[00:03:44] Clarifying the different "Copilots"[00:04:29] Inline Chat and using "Explain"[00:05:46] Selecting different AI models[00:07:39] The Chat Window: Ask, Edit, and Agent modes[00:08:06] Using context variables (@workspace, @terminal, #files)[00:11:36] Demonstrating "Ask" mode[00:14:33] Demonstrating "Edit" mode[00:16:24] Demonstrating "Agent" mode[00:22:36] Custom instructions and specifications[00:25:42] How Copilot works behind the scenes (Proxy & Safety)[00:27:00] Conclusion#GitHubCopilot #VSCode #AIcoding #SoftwareDevelopment #TwoVoiceDevs #GH300 #Certification #DeveloperTools #Programming #TechPodcast

Mark Tucker and Allen Firstenberg dive into Microsoft Copilot Studio, alow-code tool for creating conversational agents with a focus onenterprise integrations. Mark demonstrates how to build a file uploadagent that summarizes invoices using a Large Language Model (LLM). Theyexplore the studio's interface, including topics, triggers, and thedesigner canvas, while comparing it to familiar tools like Dialogflow.The discussion also touches on the concept of autonomous agents, flowsthat can be triggered by events like emails, and Microsoft's strongpush for enterprise adoption.[00:00:00] Welcome and Introduction[00:00:49] Introducing Microsoft Copilot Studio[00:02:09] Creating a New Agent[00:05:08] Understanding Topics and Triggers[00:06:57] Testing the Agent: Greeting Topic[00:10:44] Building a File Upload Agent[00:12:37] Implementing the File Upload Logic[00:15:29] Summarizing Invoices with LLMs[00:17:08] Enterprise Tools and Connectors[00:19:00] Flows and Server-Side Triggers[00:21:33] Deployment and Channels[00:23:10] Agents vs. Bots: Autonomous Capabilities[00:24:44] Comparisons with Dialogflow and Google's Ecosystem#MicrosoftCopilotStudio #CopilotStudio #LowCode #AI#ArtificialIntelligence #Chatbots #ConversationalAI #EnterpriseAI#Dialogflow #CCAI #LLM #GenerativeAI #TwoVoiceDevs #Developer #TechPodcast

Allen and Mark return after a hiatus for their annual Thanksgiving episode. They reflect on a busy year, expressing deep gratitude for the community's concern and support. The conversation explores the vital importance of human connection in a tech-centric world, the impact of mentorship, and finding balance between passion projects and life outside of work.[00:00:00] Welcome back & addressing the hiatus[00:01:38] Professional gratitude & new projects[00:02:22] The kindness of the community[00:03:58] The importance of human connection in tech[00:05:40] Reflecting on family, friends, and blessings[00:07:48] The lasting impact of mentorship[00:09:12] Balancing technology and life#Thanksgiving #Gratitude #TechCommunity #Mentorship #WorkLifeBalance #HumanConnection #TwoVoiceDevs #VoiceTech #DeveloperLife

Join Allen Firstenberg and Noble Ackerson in a deep dive into the evolving world of AI agent protocols. In this episode of Two Voice Devs, they unpack the Agent-to-Agent (A2A) protocol, comparing it with the Model Context Protocol (MCP). They explore the fundamental differences, from A2A's conversational, stateful nature to MCP's function-call-like structure. The discussion also touches on the new Agent Payment Protocol (AP2) and its potential to revolutionize how AI agents interact and transact. Is A2A the key to unlocking a future of autonomous, ambient AI? Tune in to find out![00:01:00] What is the A2A protocol?[00:04:00] A2A vs. Model Context Protocol (MCP)[00:10:00] What does A2A bring that MCP doesn't?[00:15:00] Ambient and Autonomous Agents[00:19:00] A2A solves the "Tower of Babel" problem[00:24:00] The difference between A2A and MCP: stateful vs. stateless[00:27:00] Agent Payment Protocol (AP2)[00:33:00] What does A2A promise for autonomous agents?[00:38:00] Downsides and challenges of A2A[00:44:00] Google, Gemini, and the future of A2A#A2A #MCP #AI #ArtificialIntelligence #AgentToAgent #ModelContextProtocol #TwoVoiceDevs #TechPodcast #FutureOfAI #AutonomousAgents #AIAgents #AP2 #AgentPaymentProtocol #GoogleGemini #Anthropic

Allen and Mark are back to discuss AI agent frameworks again. This time, Allen compares Google's Agent Development Kit (ADK) with LangChainJS and LangGraphJS. He walks through building a simple agent in both frameworks, highlighting the differences in their approaches, from configuration by convention in ADK to the explicit configuration in LangGraph. They also explore the web-based testing environments for both, showing how each allows for debugging and inspecting the agent's behavior. The discussion also touches on the upcoming LangChain version 1.0 and its focus on backward compatibility.[00:00:00] - Introduction[00:01:09] - Comparing agent frameworks: Google's ADK and LangChainJS[00:02:20] - A look at the ADK code[00:06:55] - A look at the LangChainJS code[00:13:20] - The web interface for testing[00:19:10] - ADK's web interface[00:22:30] - LangGraph's web interface[00:27:20] - LangGraph's state management[00:32:15] - Final thoughts#AI #AgenticAI #GoogleADK #LangChain #LangGraph #JavaScript #Python #TwoVoiceDevs

In this episode of Two Voice Devs, Mark and Allen dive into the new experimental Text-to-Speech (TTS) model in Google's Gemini 2.5. They explore its capabilities, from single-speaker to multi-speaker audio generation, and discuss how it's a significant leap from the old days of SSML. They also touch on how this new technology can be integrated with LangChainJS to create more dynamic and natural-sounding voice applications. Is this the return of voice as the primary interface for AI?[00:00:00] Introduction[00:00:45] Google's new experimental TTS model for Gemini[00:01:55] Demo of single-speaker TTS in Google's AI Studio[00:03:05] Code walkthrough for single-speaker TTS[00:04:30] Lack of fine-grained control compared to SSML[00:05:15] Using text cues to shape the TTS output[00:06:20] Demo of multi-speaker TTS with a script[00:09:50] Code walkthrough for multi-speaker TTS[00:11:30] The model is tuned for TTS, not general conversation[00:12:10] Using a separate LLM to generate a script for the TTS model[00:13:30] Code walkthrough of the two-function approach with LangChainJS[00:16:15] LangChainJS integration details[00:19:00] Is Speech Markdown still relevant?[00:21:20] Latency issues with the current TTS model[00:22:00] Caching strategies for TTS[00:23:30] Voice as the natural UI for AI[00:25:30] Outro#Gemini #TTS #VoiceAI #VoiceFirst #AI #Google #LangChainJS #LLM #Developer #Podcast

Join Allen and Mark as they take a first look at the newly released GPT-5 from OpenAI. They dive into the details of what's new, what's changed, and what's missing, frequently comparing it to other models like Google's Gemini. From the new mini and nano models to the pricing wars with competitors, they cover the landscape of the latest LLM offerings. They also discuss the new features for developers, including verbosity settings and constrained outputs with context-free grammars, and what this means for the future of AI development. Is GPT-5 the leap forward everyone was expecting, or a sign that the rapid pace of AI evolution is starting to plateau? Tune in to find out![00:00:00] Introduction and the hype around GPT-5[00:01:00] Overview of GPT-5, mini, and nano models[00:02:00] The new "thinking" model and smart routing[00:03:00] Simplifying models for developers[00:04:00] Reasoning levels vs. Gemini's "thinking budget"[00:06:00] Pricing wars and new models[00:07:00] OpenAI's new open source models[00:08:00] New verbosity setting for developers[00:09:00] Constrained outputs and context-free grammars[00:12:00] Using LLMs to translate to well-defined data structures[00:14:00] Reducing hallucinations and medical applications[00:16:00] Knowledge cutoff dates for the new models[00:18:00] Coding with GPT-5 and IDE integration[00:19:00] More natural conversations with ChatGPT[00:21:00] Missing audio and image modalities vs. Gemini[00:22:00] Community reaction to the GPT-5 release[00:24:00] The future of LLMs: Maturing and plateauing[00:26:00] The need for better developer tools and agentic computing#GPT5 #OpenAI #LLM #AI #ArtificialIntelligence #Developer #TechTalk #Podcast #AIDEvelopment #MachineLearning #FutureOfAI #AGI #GoogleGemini #TwoVoiceDevs

Join Mark and Allen in this episode of Two Voice Devs as they explore the fascinating world of AI agents. They break down what agents are, how they work, and what sets them apart from earlier AI technologies. The discussion covers key concepts like "context engineering," and the essential components of an agentic system, including prompts, RAG, memory, tools, and structured outputs.Using a practical example of a prescription management chatbot for veterans, they demonstrate how agents can handle complex tasks. They compare various frameworks for building agents, specifically focusing on OpenAI's Agent SDK (for TypeScript) and Microsoft's Semantic Kernel (for C#). They also touch on other popular frameworks like LangGraph and Google's Agent Developer Kit.Tune in for a detailed comparison of how OpenAI's Agent SDK and Microsoft's Semantic Kernel handle state, tools, and the overall agent lifecycle, and learn what the future holds for these intelligent systems.[00:00:00] - Introduction[00:01:02] - What is an AI Agent?[00:03:12] - Context Engineering and its components[00:06:02] - The role of the Agent Controller[00:08:01] - Agent Mode vs. Agent AI[00:09:36] - Use Case: Prescription Management Chatbot[00:13:42] - Handling Large Lists of Data[00:16:15] - Tools and State Management[00:21:05] - Filtering and Searching with Tools[00:27:08] - Displaying Information and Iterating through lists[00:30:10] - The power of LLMs in Agentic Systems[00:35:18] - Sub-agents and the future of agentic systems[00:38:25] - Comparing different Agent Frameworks[00:39:00] - Wrap up#AIAgents #TwoVoiceDevs #ContextEngineering #OpenAIAgentSDK #SemanticKernel #LangGraph #GoogleADK #LLMs #GenAI #AI #Developer #Podcast #TypeScript #CSharp

Join Mark and Allen for a very special 250th episode as they celebrate five years of Two Voice Devs! You won't want to miss the unique, AI-animated opening that takes them to new heights, or the special closing that brings it all home, both created with the help of Veo 3. In between, they take a look back at the evolution of voice and AI technology. From the early days of Alexa and Google Assistant to the rise of LLMs and generative AI, they discuss the shifts in the industry, the enduring importance of context, and what the future might hold for agentic AI, security, and the developer experience.[00:02:45] - Where did we think the industry would be in 5 years?[00:05:30] - How LLMs and Generative AI changed the landscape[00:11:05] - Context Engineering is the new Prompt Engineering[00:14:30] - The explosion of frameworks, libraries, and models[00:18:00] - The importance of guardrails and security[00:22:30] - Where are things going in the near term?[00:27:30] - The future of devices and developer platforms[00:30:00] - Right-sizing models and the cost of AI[00:33:30] - The importance of community and having fun#TwoVoiceDevs #VoiceAI #ArtificialIntelligence #LLMs #GenerativeAI #AIAgents #VoiceFirst #TechPodcast #ConversationalAI #AICommunity #FutureOfTech #AIEthics #AISecurity #DeveloperExperience #HotAirBalloon #Veo3

In this episode, guest host Andrew Connell, a Microsoft MVP of 21 years, joins Allen to unravel the complexities of Microsoft's AI strategy, particularly within the enterprise. They explore the world of Microsoft 365 Copilot, distinguishing it from the broader AI landscape and consumer tools like ChatGPT. Andrew provides an insider's look at how Copilot functions within a secure, private "enclave," leveraging a "Semantic Index" of your organization's data to provide relevant, contextual answers.The conversation then shifts to the developer experience. Discover the different ways developers can extend and customize Copilot, from low-code solutions in Copilot Studio to creating powerful "declarative agents" with JSON and even building "custom engine agents" where you can bring your own models and infrastructure. If you've ever wondered what Microsoft's AI story is for businesses and internal developers, this episode provides a comprehensive and honest overview.Timestamps:[00:00:01] - Introducing guest host Andrew Connell[00:00:54] - What is a Microsoft 365 developer?[00:01:40] - Andrew's journey into the Microsoft ecosystem[00:05:00] - 21 years as a Microsoft MVP[00:06:15] - Enterprise Cloud vs. Developer Cloud[00:08:06] - Microsoft's AI focus for the enterprise[00:10:57] - What is Microsoft 365 Copilot?[00:13:07] - How Copilot ensures data privacy with a "secure enclave"[00:14:58] - Understanding the Semantic Index[00:16:31] - Is Copilot a Retrieval Augmented Generation (RAG) system?[00:17:23] - Responsible AI in the Copilot stack[00:19:19] - The developer story for extending Copilot[00:22:43] - Building declarative agents with JSON and YAML[00:25:05] - Using actions and tools with agents[00:27:00] - How agents are deployed via Microsoft Teams[00:32:48] - Where does Copilot actually run?[00:36:20] - Key takeaways from Microsoft Build[00:41:20] - The spectrum of development: low-code to full-code[00:43:00] - Full control with Custom Engine Agents[00:49:30] - Where to find Andrew Connell onlineHashtags:#Microsoft #AI #Copilot #Microsoft365 #Azure #SharePoint #MicrosoftTeams #MVP #Developer #Podcast #Tech #EnterpriseSoftware #CloudComputing #ArtificialIntelligence #Agents #LowCode #NoCode #RAG

Join Allen Firstenberg and guest host Isaac Johnson, a Google Developer Expert with a deep background in DevOps and SRE, as they dive into the world of command-line AI assistants. In this episode, they compare and contrast two powerful tools: Anthropic's Claude Code CLI and Google's Gemini CLI.Isaac shares his journey from coding with Fortran in the 90s to becoming a GDE, and explains why he often prefers the focused, context-aware power of a CLI tool over crowded IDE integrations. They discuss the pros and cons of each approach, from ease of use and learning curves to the critical importance of using version control as a safety net.The conversation then gets practical with a live demo where both Claude and Gemini are tasked with generating system architecture diagrams for a real-world project. Discover the differences in speed, cost, output, and user experience. Plus, learn how to customize Gemini's behavior with `GEMINI.md` files and explore fascinating use cases beyond just writing code, including podcast production, image generation, and more.[00:00:30] - Introducing the topic: AI assistants in the command line.[00:01:00] - Guest Isaac Johnson's extensive background in tech.[00:03:00] - Why use a CLI tool instead of an IDE plugin?[00:07:30] - Pro Tip: Always use Git with AI coding tools![00:09:30] - The cost of AI: Comparing Claude's and Gemini's pricing.[00:12:15] - The benefits of Gemini CLI being open source.[00:17:30] - Live Demo: Claude Code CLI generates a system diagram.[00:21:30] - Live Demo: Gemini CLI tackles the same task.[00:27:30] - Customizing your AI with system prompts (`GEMINI.md`).[00:31:30] - Beyond Code: Using CLI tools for podcasting and media generation.[00:40:30] - Where to find and connect with Isaac Johnson.#AI #DeveloperTools #CLI #Gemini #Claude #GoogleCloud #Anthropic #TwoVoiceDevs #TechPodcast #SoftwareDevelopment #DevOps #SRE #AIassistant #Coding #Programming #FirebaseStudio #Imagen #Veo

John Gillilan, our official Apple correspondent, returns to Two Voice Devs to unpack the major announcements from Apple's latest Worldwide Developer Conference (WWDC). After failing to ship the ambitious "Apple Intelligence" features promised last year, how did Apple address the elephant in the room? We dive deep into the new "Foundation Models Framework," which gives developers unprecedented access to on-device LLMs. We explore how features like structured data output with the "Generable" macro, "Tools" for app integration, and trainable "Adapters" are changing the game for developers. We also touch on the revamped speech-to-text, "Visual Intelligence," "Swift Assist" in Xcode, and the mysterious "Private Cloud Compute." Join us as we analyze Apple's AI strategy, the internal reorgs shaping their product future, and the competitive landscape with Google and OpenAI.[00:00:00] Welcome back, John Gillilan![00:01:00] What was WWDC like from an insider's perspective?[00:06:00] Apple's big miss: What happened to last year's AI promises?[00:12:00] The new Foundation Models Framework[00:16:00] Structured data output with the "Generable" macro[00:19:00] Extending the LLM with "Tools"[00:22:00] Fine-tuning with trainable "Adapters"[00:28:00] Modernized on-device Speech-to-Text[00:29:00] "Visual Intelligence" and app integration[00:32:00] The powerful "call model" block in Shortcuts[00:36:00] Swift Assist and BYO-Model in Xcode[00:39:00] Inside Apple's big AI reorg[00:42:00] The Jony Ive / OpenAI hardware mystery[00:45:00] How Apple, Google, and OpenAI will compete and collaborate#Apple #WWDC #AI #AppleIntelligence #FoundationModels #LLM #OnDeviceAI #Swift #iOSDev #Developer #TechPodcast #TwoVoiceDevs #Siri #SwiftAssist #OpenAI #GoogleGemini #GoogleAndroid

Join Allen Firstenberg and Mark Tucker as they dive into Google's latest Gemini 2.5 models and their much-touted "thinking" capabilities. In this episode, they explore whether these models are genuinely reasoning or just executing sophisticated pattern matching. Through live tests in Google's AI Studio, they pit the Pro, Flash, and Flash-Lite models against tricky riddles, analyzing the "thought process" behind the answers. The discussion also covers the practical implications for developers, the challenges of implementing these features in frameworks like LangChainJS, and the broader question of what this means for the future of AI.[00:00:00] - Introduction to Gemini 2.5 "thinking" models[00:01:00] - How "thinking" models relate to Chain of Thought prompting[00:03:00] - Advantages of separating reasoning from the answer[00:05:00] - Exploring the models (Pro, Flash, Flash-Lite) in AI Studio[00:06:00] - Thinking mode and thinking budget explained[00:09:00] - Test 1: Strawberry vs. Triangle[00:15:00] - Test 2: The "bricks vs. feathers" riddle with a twist[00:17:00] - Prompting the model to ask clarifying questions[00:25:00] - Is it reasoning or just pattern matching?[00:28:00] - Practical applications and the future of these models[00:35:00] - Implementing reasoning models in LangChainJS[00:40:00] - Conclusion#AI #GoogleGemini #ReasoningModels #ThinkingModels #LLM #ArtificialIntelligence #MachineLearning #LangChain #Developer #Podcast #TechTalk #TwoVoiceDevs

Ever find that the best way to understand a new framework is to build it yourself? In this episode of Two Voice Devs, Mark Tucker takes us on a deep dive into Crew AI, a powerful Python framework for orchestrating multi-agent AI systems.To truly get under the hood, Mark decided to port the core functionality into TypeScript, creating "JCrew AI." This process provides a unique and insightful perspective on how these agent-based systems are designed. Join us as we deconstruct the core concepts of Crew AI, exploring how it simplifies the complex process of making AI agents collaborate effectively. We discuss everything from the fundamental building blocks—like agents, tasks, and crews—to the clever ways it implements prompt engineering best practices.If you're a developer interested in the architecture of modern AI applications, you'll gain a clear understanding of how to define agent roles, backstories, and goals; how to chain tasks together; and how the underlying execution loop (and its similarity to the ReAct pattern) works to produce cohesive results.Timestamps:[00:00:00] - Introduction[00:01:00] - What is Crew AI and the "JCrew AI" Learning Project[00:04:00] - Core Concepts: How Crews, Agents, and Tasks Work[00:06:00] - Anatomy of a Crew AI Agent (Role, Goal, Backstory)[00:10:00] - Building Prompts with Templates and "Slices"[00:15:00] - The Execution Flow: From "Kickoff" to Final Output[00:21:00] - Under the Hood: The Agent Executor and Core Logic Loop[00:23:00] - How Crew AI Compares to LangChain and LangGraph[00:28:00] - Practical Considerations: Human-in-the-Loop and Performance[00:30:00] - Learning a Framework by Rebuilding It#AI #ArtificialIntelligence #Developer #SoftwareEngineering #CrewAI #MultiAgentSystems #AIAgents #Python #TypeScript #PromptEngineering #LLM #Podcast

What do Anthropic's latest announcements mean for developers? In this episode, Allen is joined by freelance conversation designer Valentina Adami to break down all the major news from the recent "Code with Claude" event.Valentina shares her hands-on experience and perspective on the new Opus 4 and Sonnet 4 models, discussing their distinct capabilities, the new "reasoning" features, and why Anthropic's transparency with its public system prompt is a game-changer. They also explore Claude Code, the new coding assistant that runs in your terminal, and how it can be used for everything from fixing bugs to learning new frameworks.Finally, they cover the latest integrations for the Model Context Protocol (MCP) and the long-awaited addition of web searching to Claude, examining how these tools are evolving and what it means for the future of AI-assisted development.Timestamps:[00:41] Guest Valentina Adami's background in humanities and tech[06:17] What's new in the Opus 4 and Sonnet 4 models?[14:40] Are the models "thinking" or "reasoning"?[19:27] The latest on MCP (Model Context Protocol) integrations[25:03] Exploring the new coding assistant: Claude Code[31:37] Claude can now search the web#Anthropic #ClaudeAI #Opus4 #Sonnet4 #ThinkingAI #ReasoningAI #LLM #DeveloperTools #GenerativeAI #AI #Claude #CodingAssistant #MCP #ModelContextProtocol #TwoVoiceDevs

Join Allen Firstenberg and Michal Stanislawek in this thought-provoking episode of Two Voice Devs as they unpack two recent LinkedIn posts by Michal that reveal critical insights into the security and ethical challenges of modern AI agents.The discussion kicks off with a deep dive into a concerning GitHub MCP server exploit, where researchers uncovered a method to access private repositories through public channels like PRs and issues. This highlights the dangers of broadly permissive AI agents and the need for robust guardrails and input sanitization, especially when vanilla language models are given wide-ranging access to sensitive data. What happens when your 'personal assistant' acts on a malicious instruction, mistaking it for a routine task?The conversation then shifts to the ethical landscape of AI, exploring Anthropic's Claude 4 experiments which suggest that AI assistants, under certain conditions, might prioritize self-preservation or even 'snitch.' This raises profound questions for developers and users alike: How ethical do we want our agents to be? Who do they truly work for – us or the corporation? Could governments compel AI to reveal sensitive information?Allen and Michal delve into the implications for developers, stressing the importance of building specialized agents with clear workflows, implementing principles of least privilege, and rethinking current authorization protocols like OAuth to support fine-grained permissions. They argue that we must consider the AI itself as the 'user' of our tools, necessitating a fundamental shift in how we design and secure these increasingly autonomous systems.This episode is a must-listen for any developer building with AI, offering crucial perspectives on how to navigate the complex intersection of AI capabilities, security vulnerabilities, and ethical responsibilities.More Info:* https://www.linkedin.com/posts/xmstan_the-researchers-who-unveiled-claude-4s-snitching-activity-7333733889942691840-wAQ4* https://www.linkedin.com/posts/xmstan_your-ai-assistant-may-accidentally-become-activity-7333219169888305152-2cjN00:00 - Introduction: Unpacking AI Agent Security & Ethics00:50 - The GitHub MCP Server Exploit: Public Access to Private Repos02:15 - Ethical AI: Self-Preservation & The 'Snitching' Agent Dilemma04:00 - Developer Responsibility: Building Ethical & Trustworthy AI Systems09:20 - The Dangers of Vanilla LLM Integrations Without Guardrails13:00 - Custom Workflows vs. Generic Autonomous Agents17:20 - Isolation of Concerns & Principles of Least Privilege26:00 - Rethinking OAuth: The Need for Fine-Grained AI Permissions29:00 - The Holistic Approach to AI Security & Authorization#AIAgents #AIethics #AIsecurity #PromptInjection #GitHub #ModelContextProtocol #MCP #MCPservers #MCPsecurity #OAuth #Authorization #Authentication #LeastPrivilege #Privacy #Security #Exploit #Hack #RedTeam #CovertChannel #Developer #TechPodcast #TwoVoiceDevs #Anthropic #ClaudeAI #LLM #LargeLanguageModel #GenerativeAI

Join Allen Firstenberg and Linda Lawton of Two Voice Devs as they record live from Google I/O 2025! As the conference neared the end, they dive deep into the groundbreaking announcements in generative AI, discussing the latest advancements and what they mean for developers, especially those in Conversational AI.This episode explores the new and updated models that are set to redefine content creation:Lyria: Google's innovative streaming audio generation API, its unique WebSocket-based approach, and the fascinating possibilities (and challenges!) of dynamic music creation, including its potential for YouTube content and the ever-present copyright questions surrounding AI-generated media.Veo 3: The video generation powerhouse, now enhanced with synchronized audio and voice, realistic lip-sync for characters (yes, even cartoon animals!), and improvements in "world physics." They also tackle the implications of its pricing for professional and individual creators.Imagen 4: Discover the highly anticipated improvements in text generation within images, including stylized fonts and potential for other languages.Allen and Linda also share some early creations with these new models.Whether you're building the next great voice app, creating dynamic content, or just curious about the cutting edge of AI, this episode offers a developer-focused perspective on the future of generative media.00:00:00: Introduction to Two Voice Devs at I/O 202500:00:50: I/O 2025: New Generative AI Models Overview00:01:20: Lyria: Streaming Audio Generation and Documentation Challenges00:03:00: Lyria's Practical Use Cases & Generative AI Copyright Questions00:10:00: Veo 3: Video Generation with Synchronized Audio and Voice Features00:12:10: Veo 3 Pricing and Cost Implications for Developers00:14:20: Imagen 4: Improved Text Generation in Images00:17:40: Professional Use Cases for Veo and Imagen00:19:10: Flow: The New Professional Studio System for Creators00:22:00: Gemini Ultra Tiered Pricing and Regional Restrictions00:24:20: Concluding Thoughts and Call to Action#GoogleIO2025 #GenerativeAI #AIModels #Lyria #Veo3 #Imagen4 #FlowAI #TwoVoiceDevs #VoiceTech #ConversationalAI #AIDevelopment #MachineLearning #ContentCreation #YouTubeCreators #GoogleAI #VertexAI #GeminiUltra #CopyrightAI #TechPodcast

Recorded live from the podcast space at I/O, Allen Firstenberg and Roya dive into the overwhelming, yet incredibly exciting, world of AI announcements permeating the conference this year.They discuss the pervasive theme of AI augmenting human intelligence rather than replacing it, exploring concrete examples across various domains. From breakthroughs in mathematics with AlphaProof to the efficiency gains of the new Gemma 3 model (running on small devices with a tiny memory footprint and reduced environmental impact), they cover the cutting edge of AI research and application.Discover how models like CoScientists and Notebook LM are revolutionizing research and productivity (including generating podcasts from your notes!), the advancements in Gemini's audio output for more natural and multilingual conversations, and the potential for intelligence explosion with Alpha Evolve. Allen and Roya also unpack the fascinating Gemini Diffusion model's application to text and code generation and the critical role of AI in healthcare with the Amy model.The conversation wouldn't be complete without tackling the big question: the AGI (Artificial General Intelligence) debate. Is it coming soon, or is it still a distant concept? Join Allen and Roya for their perspectives straight from the heart of Google I/O.Tune in to get a developer's perspective on the future of AI driven by the latest announcements from Google I/O!00:00 - Intro & AI Everywhere at I/O01:36 - The Core Theme: AI Augments Humans01:55 - AI in Math: AlphaProof04:30 - Gemma 3: Small, Efficient, Open Models07:07 - AI for Researchers: CoScientists & Notebook LM10:05 - Enhanced Audio: Gemini Voice & Translation12:09 - Alpha Evolve: Feedback Loops & Intelligence Explosion14:15 - Gemini Diffusion: Diffusion for Text & Code21:11 - AI in Healthcare: The Amy Model22:08 - The AGI Debate: Is it Coming?#GoogleIO #IO2025 #AI #MachineLearning #DeepLearning #GeminiAI #GemmaAI #DiffusionModels #NotebookLM #HealthcareAI #AGI #ArtificialGeneralIntelligence #TwoVoiceDevs #TechPodcast #Developers #ConversationalAI

The buzz from Google IO 2025 is deafening, especially about the new smart glasses announcement! On this episode of Two Voice Devs, Allen Firstenberg and Noble Ackerson — former Google Glass Explorers themselves — dive deep into their first impressions of Google's Project Astra / Android XR / Gemini glasses prototype.Drawing on their unique experience from the early days of Glass, Allen and Noble discuss the evolution of wearable computing, the collision of conversational AI (Gemini) and spatial computing (Android XR), and what this new device means for the future.They share their thoughts on the hardware design, the user interface (is it Gemini, Android XR, or both?), and critically examine the product strategy compared to Glass and other devices like the Apple Vision Pro. Most importantly for developers, they ponder the crucial question: what is the developer story here? Is Google providing the necessary tools and documentation, or are we repeating past mistakes?Tune in for a candid, experienced perspective on Google's latest foray into smart glasses and whether this iteration truly builds on the lessons learned from the past.0:00:30 - Introduction: Google IO buzz and the glasses question0:01:16 - Remembering Google Glass: First impressions & the "art of the possible"0:02:35 - From Glass to Assistant: The evolution of ubiquitous computing0:03:42 - The Collision: Conversational AI meets Spatial Computing0:03:58 - First Impressions: Trying on the new Google glasses prototype at IO0:04:25 - How Glass Shaped Us: Focusing on human factors and product strategy0:05:44 - The "If You Build It They Will Come" Trap: Why problem-solving is key0:07:48 - Contrasting with Apple Vision Pro & the "Start with VR" concern0:09:14 - Breaking Down the Stack: Hardware, Android XR, and Gemini0:14:24 - Hardware Deep Dive: Weight, balance, optics, and the lower display decision0:18:38 - UI/Interaction Discussion: Gemini's role, gestures, voice/tap inputs0:19:37 - The Developer Story: Lack of clarity and need for APIs/documentation0:27:55 - Rapid Fire: Best thing & Biggest Irk point about the prototype0:32:16 - The Big Question: Would we buy one today?0:33:08 - Final Thoughts: Value proposition and learning from Glass#AndroidXR #Gemini #GoogleGlass #GoogleIO #IO2025 #ProjectAstra #SmartGlasses #WearableTech #SpatialComputing #ConversationalAI #VoiceFirst #VoiceDevs #GlassExplorers #TechPodcast #DeveloperLife #HumanComputerInteraction #ProductStrategy #Google #GoogleDeepMind #DeepMind

Join us on Two Voice Devs as Allen Firstenberg talks with Rizel Scarlett, Tech Lead for Open Source Developer Relations at Block. Rizel shares her fascinating journey from psychology student to software engineer and now a leader in developer advocacy, highlighting her passion for teaching and creative problem-solving.The conversation dives deep into Block's innovative open source work, particularly their AI agent called Goose, which leverages the Model Context Protocol (MCP). Rizel explains what MCP is, seeing it as an SDK or API for AI agents, and discusses the excitement around its potential to democratize coding and other tools for developers and non-developers alike, sharing compelling use cases like automating tasks in Google Docs and interacting with Blender.However, the discussion doesn't shy away from the critical challenges facing MCP, especially concerning security. Rizel addresses concerns about trusting community-built MCP servers, potential vulnerabilities, and mitigation strategies like allow lists and building internal, vetted servers. They also explore the complexities of exposing large APIs, the demand for local AI for privacy, the current limitations of local models, and the user experience of installing and trusting MCP plugins.Rizel shares examples of promising MCP servers, including those focused on "long-term memory" and, notably, a speech/voice-controlled coding server, bringing the conversation back to the show's roots in voice development and accessibility, touching upon the concept of temporary disability.The episode concludes by reflecting on whether MCP is currently a "small, beginner solution" being hyped as a "massive, full-featured" one, the need for more honest conversations about its limitations, and the ongoing efforts within the community and companies like Block to improve the protocol, including discussions around official registries and easier installation methods like deep links.Tune in for a candid look at the exciting, yet challenging, landscape of AI agents, MCP, and open source development.More Info:* Goose - https://github.com/block/goose* Pieces for Developers - https://pieces.app/features/mcp* Speech MCP - https://glama.ai/mcp/servers/@Kvadratni/speech-mcp[00:00:48] Meet Rizel Scarlett & Her Career Journey (Psychology to Dev Advocacy)[00:03:54] Introducing Block & Its Mission (Square, Cash App, etc.)[00:04:58] Block's Open Source Division and the Goose AI Agent[00:05:48] Diving into the Model Context Protocol (MCP)[00:07:56] What is MCP? (SDK for Agents) & Exciting Use Cases (Democratization, non-developers)[00:10:36] Major Security Concerns with MCP (Trust, vulnerabilities, typo squatting)[00:11:48] Mitigation Strategies & Authentication (Allow Lists, Internal Servers, Vetting)[00:17:59] The Current State of MCP: An Infancy Protocol[00:20:09] Complexity & Context Window Challenges with MCP Servers[00:23:14] User Demand for Local AI & Data Privacy[00:25:31] User Experience of MCP Plugin Installation & Trust[00:28:42] Examples of Useful MCP Servers (Pieces, Computer Controller, Speech)[00:31:18] The Power of Voice-Controlled Coding (Accessibility, temporary disability)[00:33:59] MCP: Hype vs. Reality & The Need for Honest Conversations[00:36:00] Efforts to Improve MCP (Committees, Registries, Deep Links)#developer #programming #tech #opensource #block #ai #aigent #llm #mcp #modelcontextprotocol #devrel #developeradvocacy #security #cybersecurity #privacy #localai #remoteai #accessibility #voicecoding #riselscarlett #gooseai

How do you know if a Large Language Model is good for your specific task? You benchmark it! In this episode, Allen speaks with Amy Russ about her fascinating career path from international affairs to data, and how that unique perspective now informs her work in LLM benchmarking.Amy explains what benchmarking is, why it's crucial for both model builders and app developers, and how it goes far beyond simple technical tests to include societal, cultural, and ethical considerations like preventing harms.Learn about the complex process involving diverse teams, defining fuzzy criteria, and the technical tools used, including data versioning and prompt template engines. Amy also shares insights on how to get involved in open benchmarking efforts and where to find benchmarks relevant to your own LLM projects.Whether you're building models or using them in your applications, understanding benchmarking is key to finding and evaluating the best AI for your needs.Learn More:* ML Commons - https://mlcommons.org/Timestamps:00:18 Amy's Career Path (From Diplomacy to Data)02:46 What Amy Does Now (Benchmarking & Policy)03:38 Defining LLM Benchmarking05:08 Policy & Societal Benchmarking (Preventing Harms)07:55 The Need for Diverse Benchmarking Teams09:55 Technical Aspects & Tooling (Data Integrity, Versioning)10:50 Prompt Engineering & Versioning for Benchmarking12:48 Preventing Models from Tuning to Benchmarks15:30 Prompt Template Engines & Generating Prompts17:10 Other Benchmarking Tools & Testing Nuances19:10 Benchmarking Compared to Traditional QA21:45 Evaluating Benchmark Results (Human & Metrics)23:05 The Challenge of Establishing an Evaluation Scale23:58 How to Get Started in Benchmarking (Volunteering, Organizations)25:20 Open Benchmarks & Where to Find Them26:35 Benchmarking Your Own Model or App28:55 Why Benchmarking Matters for App Builders29:55 Where to Learn More & Follow AmyHashtags:#LLM #Benchmarking #AI #MachineLearning #GenAI #DataScience #DataEngineering #PromptEngineering #ModelEvaluation #TechPodcast #Developer #TwoVoiceDevs #MLCommons #QA

Join Allen Firstenberg from Google Cloud Next 2025 as he sits down with Ankur Kotwal, Google's Global Head of Cloud Advocacy. In this episode of Two Voice Devs, Allen and Ankur dive deep into the world of Developer Relations (DevRel) at Google, discussing its crucial role as a bridge connecting Google's product teams and engineers with the global developer community.Ankur shares his fascinating personal journey, from coding BASIC as a child alongside his developer dad to leading a key part of Google Cloud's developer outreach. They explore the ever-evolving landscape of technology, using the metaphor of "waves" – from early desktop computing and the internet to mobile apps and the current tidal wave of AI and "vibe coding."This conversation offers valuable insights for all developers navigating the pace of technological change. Discover what Developer Relations is and how it serves as that essential bridge, functioning bidirectionally (both outbound communication and inbound feedback). Learn about the importance of community programs like Google Developer Experts (GDEs), and how developers can effectively connect with DevRel teams to share their experiences and help shape the future of products. Ankur and Allen also reflect on the need for continuous learning, understanding underlying tech layers, and the shared passion that drives innovation in our industry.Whether you're a long-time developer or just starting out, learn how to ride the waves, connect with peers, and make your voice heard in the developer ecosystem by engaging with the DevRel bridge.More Info:* Google Developers Program: https://goo.gle/google-for-developersTimestamps:00:49 - Ankur's Role as Global Head of Cloud Advocacy01:48 - The Bi-directional Nature of Developer Relations02:34 - Ankur's Journey into Tech and DevRel09:47 - What is Developer Relations? (The DevRel Bridge Explained)12:06 - The Value of Community and Google Developer Experts (GDEs)14:08 - Allen's Motivation for Being a GDE18:24 - Riding the Waves of Technological Change (AI, Vibe Coding)20:37 - The Importance of Understanding Abstraction Layers25:41 - How Developers Can Engage with the DevRel Bridge30:50 - Providing Feedback: Does it Make a Difference?Hashtags:#DeveloperRelations #DevRel #GoogleCloud #CloudAdvocacy #DeveloperCommunity #TechEvolution #AI #ArtificialIntelligence #VibeCoding #GoogleGemini #SoftwareDevelopment #Programming #Google #GoogleCloudNext #GoogleDevRel #GDG #GDE #TwoVoiceDevs #Podcast #Developers

Join Allen Firstenberg and Alice Keeler, the Two Voice Devs, live from Day 1 of Google Cloud Next 2025 in Las Vegas! In this episode, recorded amidst the energy of the show floor, Allen and Alice dive into the major announcements and highlights impacting developers, especially those interested in AI and conversational interfaces.Alice, known as the "Queen of Spreadsheets" and a Google Developer Expert for Workspace and App Sheet, shares her unique perspective on using accessible tools like App Script for real-world solutions, contrasting it with the high-end tech on display.They unpack the new suite of generative AI models announced, including Veo for video, Chirp 3 for audio, Lyric for sound generation, and updates to Imagen, all available on Vertex AI. They recount the breathtaking private premiere at Sphere, discussing how Google DeepMind's cutting-edge AI enhanced the classic Wizard of Oz film, expanding and interpolating scenes that never existed – and connect this advanced technology back to tools developers can use today.A major focus is the new Agent Builder, a tool poised to revolutionize how developers create multimodal AI agents capable of natural voice, text, and image interactions, demonstrated through exciting examples. They discuss the accessibility of this tool for developers of all levels and its potential to automate tedious tasks and create entirely new user experiences.Plus, they touch on the new Agent to Agent Protocol for complex AI workflows, updates to AI Studio, and the production readiness of the Gemini 2.0 Live API.Get a developer's take on the biggest news from Google Cloud Next 2025 Day 1 and a look ahead to the developer keynote.More Info:* Google Developers Program: https://goo.gle/google-for-developers* Next 2025 Announcements: https://cloud.google.com/blog/topics/google-cloud-next/google-cloud-next-2025-wrap-up00:00:31 Welcome to Google Cloud Next 202500:01:18 Meet Alice Keeler: Math Teacher, GDE, and App Script Developer00:03:44 App Script: Accessible Development & Real-World Solutions00:05:40 Cloud Next 2025 Day 1 Keynote Highlights00:06:18 New Generative AI Models: Veo (Video), Chirp 3 (Audio), Lyric (Sound), Imagen Updates00:09:00 The Sphere Experience & DeepMind's Wizard of Oz AI Enhancement00:14:00 From Hollywood Magic to Public Tools: Vertex AI Capabilities00:16:30 Agent Builder: The Future of AI Agents & Accessible Development00:23:37 Agent to Agent Protocol: Enabling Complex AI Workflows00:25:20 Other Developer News: AI Studio Revamp & Gemini 2.0 Live API00:26:30 Connecting with Experts & Discovering What's Next#GoogleCloudNext #GCNext #LasVegasSphere #SpehereLasVegas #TwoVoiceDevs #AI #GenerativeAI #VertexAI #Gemini #AgentBuilder #AppScript #Developers #LowCode #NoCode #AIInEducation #AIDevelopment #ConversationalAI #VoiceAI #MachineLearning #WizardOfOz

Following up on our recent conversation about the Model Context Protocol (MCP), Mark and Allen take a step deeper from a developer's perspective. While still in the shallow end, they explore the TypeScript SDK, the MCP Inspector tool, and the Smithery.ai registry to understand how developers define and host MCP servers and tools.They look at code examples for both local (Standard IO) and potentially remote (Streamable HTTP) server implementations, discussing how tools, resources, and prompts are registered and interact. They also touch on the challenges of configuration, authentication, and the practical messy realities encountered when trying to use MCP tools in clients like Claude Desktop.This code dive generates more questions than answers about the practical hosting models, configuration complexities, and the vision for MCP in the AI ecosystem. Is it the USBC of AI tools, or more like a 9-pin serial port needing detailed manual setup? Join Mark and Allen as they navigate the current state of MCP code and ponder its future role.If you have insights into these complexities or are building with MCP, they'd love to hear from you!00:40 Following up on the previous MCP episode01:20 Reconsidering MCP's purpose and metaphors03:25 Practical challenges with clients (like Claude Desktop) and configuration05:00 Discussing future AI interfaces and app integration09:15 Understanding Local vs. Remote MCP servers and hosting models12:10 Comparing MCP setup to early web development (CGI)13:20 Diving into the MCP TypeScript SDK code (Standard IO, HTTP transports)23:00 Running a local MCP server and using the Inspector tool23:50 Code walkthrough: Defining tools, resources, and prompts31:15 Exploring remote (HTTP) connection options in the Inspector32:30 Introducing Smithery.ai as a potential MCP registry33:45 Navigating the Smithery registry and encountering configuration confusion36:15 Analyzing server source code vs. registry listings - Highlighting discrepancies44:30 Reflecting on the current practical usability and complexity of MCP46:10 Analogy: MCP as a serial port vs. USBC#ModelContextProtocol #MCP #AIDevelopment #DeveloperTools #Programming #TypeScript #APIs #ToolsForAI #LLMTools #TechPodcast #SoftwareDevelopment #TwoVoiceDevs #AI #GenerativeAI #Anthropic #Google #LangChain #Coding #AIAPI

Join Allen Firstenberg and Michal Stanislawek on Two Voice Devs as they dive deep into the Model Context Protocol (MCP), a proposition by Anthropic that's gaining traction in the AI landscape. What exactly is MCP, and is it the key to seamless integration of external services with large language models?In this insightful discussion, Allen and Michal unravel the complexities of MCP, exploring its potential to solve integration pain points, its current implementation challenges with local "servers," and the crucial missing pieces like robust authentication and monetization. They also discuss the implications of MCP for AI applications, compare it to established protocols, and ponder its relationship with Google's newly announced Agent to Agent (A2A) protocol.Is MCP a game-changer that will empower natural language interaction with all kinds of software, from Blender to Slack? Or are there fundamental hurdles to overcome before it reaches its full potential? Tune in to get a developer's perspective on this evolving technology and understand its possible future in the world of AI.Timestamps:00:00:55: What is MCP and what does it stand for?00:02:35: What pain points is MCP trying to solve?00:04:35: The local nature of current MCP "servers" and its implications.00:07:15: MCP as a communication protocol and the concept of "tools."00:08:35: The potential for MCP server discovery and the lack thereof currently.00:10:25: Security and trust concerns with local MCP servers.00:13:30: The intended architecture of MCP and the local server model.00:16:35: The absence of built-in authentication and authorization in MCP.00:18:35: MCP as a standardized framework and the "plugin" analogy.00:20:35: MCP's role in defining "AI apps."00:22:35: The need for a registry component for broader adoption.00:23:35: What MCP clients currently exist and the breadth of adoption.00:26:25: MCP and its application in the context of AI agents.00:29:25: What is still needed for widespread adoption of remote MCP servers?00:35:15: The concept of an MCP "meta server" or aggregator.00:38:55: How does Google's Agent to Agent (A2A) protocol fit in?00:41:45: The debate between MCP servers and specialized AI agents.00:43:15: The right level of abstraction for tool definitions.00:46:05: The future evolution of MCP and the importance of experimentation.#MCP #ModelContextProtocol #AI #LargeLanguageModels #LLM #Anthropic #Claude #ClaudeDesktop #ClaudeOS #Google #Agent2Agent #A2A #GeminiOS #ServerClient #AIAgents #Developer #TechPodcast #TwoVoiceDevs #APIs #SoftwareIntegration #FutureofAI

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.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.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.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.Timestamps:0:00:00 Introduction and Recap of Generative UI0:03:20 Demonstrating Generative UI Pitfalls with a Smart Home Dashboard0:05:15 Dynamic Adaptation and User Intent0:11:30 Accessibility and Customization in Generative UI0:13:30 Encountering Limitations and the Need for Fine-Tuning0:17:50 Introducing Fine-Tuning for LLMs: Adapting Pre-trained Models0:19:30 Fine-Tuning for New Patterns and Domain-Specific Understanding0:20:50 The Role of Training Data in Supervised Fine-Tuning0:23:30 Generalization of Patterns by LLMs0:24:20 Exploring Key Fine-Tuning Hyperparameters: Learning Rate and Training Epochs0:30:30 Demystifying Supervised Fine-Tuning and its Benefits0:33:30 Saving and Hosting Fine-Tuned Models: Hugging Face and Google Cloud Run0:36:50 Integrating Fine-Tuned Models into Applications0:38:50 The Model is Not the Product: Focus on User Value0:39:40 Closing Remarks and Teasing Future Discussions on MonitoringHashtags:#GenerativeUI #AI #LLM #LargeLanguageModels #FineTuning #MachineLearning #UserInterface #UX #Developers #Programming #SoftwareEngineering #CloudComputing #GoogleCloudRun #GoogleGemini #GoogleGemma #HuggingFace #AIforDevelopers #TechPodcast #TwoVoiceDevs #ArtificialIntelligence #TechMagic

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.Timestamps:00:00:00 - Introduction and Noble's return as a Google Developers Expert in AI00:02:00 - Defining Generative UI and distinguishing it from AI-aided design00:03:30 - Exploring potential examples of Generative UI based on user needs and context00:04:45 - The difference between traditional static UIs and dynamic generative UIs00:06:45 - How LLMs can be leveraged for real-time UI generation00:07:15 - The overlap and distinction between Generative UI and ConversationalUI00:08:30 - Challenges of Generative UI: Predictability and guiding users00:09:30 - The importance of maintaining established UX patterns in Generative UI00:12:30 - Traditional UI limitations and the promise of personalized generative UIs00:14:00 - Context-specific information access and adapting to user roles00:15:30 - An example of Generative UI in a business intelligence dashboard00:17:00 - A six-stage pipeline for how Generative UI systems might work00:19:00 - The concept of "agents on rails" in the context of UI generation00:20:30 - The reasoning and tool-calling aspects of generative UI agents00:22:30 - Tools as the core of UI generation and component recognition challenges00:24:30 - Demonstrating the dynamic generation of UI components (charts)00:27:30 - Exploring interactions and limitations of the generative UI demo00:29:15 - The "hallucination" of UI components and the need for fine-tuning00:31:30 - Conclusion and future discussion on component fine-tuning#GenerativeUI #AI #LLM #UserInterface #UX #AIDesign #DynamicUI #TwoVoiceDevs #GoogleDevelopersExperts #TechPodcast #SoftwareDevelopment #WebDevelopment #AIAgents

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!Timestamps:0:00 Why DeepSeek is creating buzz1:06 Unveiling DeepSeek's Two Key Models2:59 Understanding the Power of Attention4:12 What is the latent space?5:55 The nail salon example: Multi-Head Attention Explained10:02 The doctor/cook/police analogy: Mixture of Experts Explained13:51 AI vs. AI: DeepSeek's Cost-Saving Training Method16:01 Hallucinations: Is AI Training Too Risky?20:59 What are Reasoning Models and Why Do They Matter?26:53 LLMs are pattern systems explained28:22 How DeepSeek is using old GPUs32:53 OpenAI vs. DeepSeek: The Data Plagiarism Debate39:32 Political Correctness: The Challenge of Guardrails in AI42:16 Why Open Source is Crucial for the Future of AI43:20 Run DeepSeek locally on OLAMA43:56 Final ThoughtsHashtags: #DeepSeek #AI #LLM #Innovation #TechNews #Podcast #ArtificialIntelligence #MachineLearning #Ethics #OpenAI #DataPrivacy #Censorship #TwoVoiceDevs #DeepLearning #ReasoningModel #AIRevolution #ChinaTech

Amazon has announced Alexa Plus, powered by large language models (LLMs), and developers are buzzing with anticipation (and a healthy dose of skepticism!). Join Mark Tucker and Allen Firstenberg, your Two Voice Devs, as they dissect the news, explore the potential of the AI-native SDKs, and debate whether this overhaul will reignite the spark for Alexa development.In this deep dive, we cover:* The basics of Alexa Plus: What it is, who gets it for free, and how it differs from classic Alexa skills.* The fate of classic Alexa skills: Are they migrating, evolving, or being left behind? We explore how current skills might benefit from AI enhancements.* Alexa's New AI SDKs (Alexa+):** Action SDK: Turn your existing APIs into voice experiences. Is it all about selling stuff?** WebAction SDK: Integrate your website with Alexa using low-code workflows. But how does it really work?** Multi-Agent SDK: Surface your existing bots and agents through Alexa. What's the difference between these and existing Alexa skills?* The Big Questions: Personalization, monetization, notifications, handling hallucinations, response times, identity, and more!* And finally, our predictions! Will Alexa Plus make developing for Alexa fun again? Mark and Allen give their takes!Whether you're a seasoned Alexa developer or just curious about the future of voice interfaces, this episode is packed with insights, questions, and a healthy dose of developer humor. Subscribe to Two Voice Devs for more cutting-edge discussions on voice technology!More Info:* https://developer.amazon.com/en-US/blogs/alexa/alexa-skills-kit/2025/02/new-alexa-announce-blogTimestamps:0:00:00 Introduction0:01:00 Alexa Plus Overview0:02:00 Pricing & Classic Skills0:05:00 Access & Availability0:06:00 Alexa AI SDKs0:12:00 Action SDK0:21:00 WebAction SDK0:27:00 Multi-Agent SDK0:31:00 Big Questions for Developers0:36:00 Will Alexa Be Fun Again?0:41:00 Response Times & Notifications0:45:00 Multimodal Experiences0:46:00 Conclusion#Alexa #AlexaPlus #VoiceDevelopment #AI #LLM #Amazon #Skills #VoiceFirst #Podcast #Developer #Tech #ArtificialIntelligence #TTS #ASR # ConversationalAI

Allen Firstenberg and Linda Lawton dive deep into the power of Google's Imagen 3 Editing API. Discover how to effortlessly edit and enhance images, opening up a world of creative possibilities for developers!* Learn how the In-Painting/In-filling feature can quickly remove wires from an image, add highlights, and correct shading on images that the AI generated, and more.* Explore how to create your own 3D-printed objects from scratch using AI.* Discover how you can reference images to put models or products into a specific scene.* Learn how to use the Out-Painting feature to extend images beyond their original boundaries, transforming portraits into landscapes and beyond.Also, be prepared for some unexpected and hilarious AI hallucinations along the way as Allen tries to zoom out from an image multiple times! Plus, the duo discusses the ethical implications of AI-generated content and how creatives can leverage these tools to enhance their own artwork.Don't miss this exciting exploration of Imagen 3 and its potential to revolutionize image manipulation for developers and creators alike!Timestamps:00:00:00 Introduction00:00:55 Imagen 3 Editing API00:04:36 In-Painting/In-Filling00:04:52 Generating 3D Models00:09:00 Vertex AI Studio00:10:15 Imagen and Gemini Together00:13:14 Generating Images with Reference Images00:20:11 Out-Painting00:31:00 Ethical Implications#Imagen3 #AI #ImageEditing #GoogleAI #VertexAI #VertexAISprint #MachineLearning #DeveloperTools #GenerativeAI #GenAI #3DPrinting #AIArt

Are you building AI models and systems? Then you need to understand AI ethics! In this episode of Two Voice Devs, Allen Firstenberg welcomes Parul, a Senior Production Engineer at Meta, to dive deep into the world of AI ethics. Learn why fairness and bias are critical considerations for developers, and discover practical techniques to mitigate bias in your AI systems.Parul shares her experiences and passion for AI ethics, detailing how biases in training data and system design can lead to unfair or even harmful outcomes. This episode provides concrete examples, actionable advice, and valuable resources for developers who want to build more ethical and equitable AI.More Info:* Fairlearn: https://fairlearn.org/* AIF360: https://aif360.readthedocs.io/en/stable/* what-if tool: https://pair-code.github.io/what-if-tool/Timestamps:00:00:00 Introduction00:00:20 Guest Introduction: Parul, Meta00:02:22 What is AI Ethics?00:06:13 Why is AI Ethics Important?00:08:15 AI Systems vs. AI Models00:09:52 Examples of Bias in AI Systems00:12:23 Minimizing Biases: Developer Responsibility00:14:53 Tips for Minimizing Unfairness and Biases00:19:40 Fairness Constraints: Demographic Parity00:23:17 The Bigger Picture: Roles & Responsibilities00:29:23 Monitoring: Bias Benchmarks00:32:00 Open Source Frameworks for AI Ethics00:34:02 Call to Action & Closing#AIethics #Fairness #Bias #MachineLearning #ArtificialIntelligence #Developers #OpenSource #EthicalAI #TwoVoiceDevs #TechPodcast #DataScience #AIdevelopment

Are you overwhelmed by the sheer number of Large Language Models (LLMs) available? Choosing the right LLM for your project isn't about picking the most popular one – it's about understanding your specific needs and rigorously evaluating your options.In this episode of Two Voice Devs, Allen Firstenberg and guest host Brad Nemer, a seasoned product manager, dive deep into the world of LLM evaluation. They go beyond the marketing buzz and explore practical tools and strategies for making informed decisions.Whether you're a developer, a product manager, or just curious about the practical applications of LLMs, this episode provides invaluable insights into making the right choices for your projects. Don't get caught up in the hype – learn how to evaluate LLMs effectively!More Info:https://www.udacity.com/blog/2025/01/how-to-choose-the-right-ai-model-for-your-product.html[00:00:00] Introduction: Meet Brad Niemer[00:00:38] Brad's Journey to Product Management & AI[00:03:12] Collaboration with Noble Ackerson and the LLM Evaluation Challenge[00:05:23] The Role of a Product Manager.[00:07:43] Product manager relation to engineering.[00:13:46] Exploring Evaluation Tools: Hugging Face[00:16:58] Exploring Evaluation Tools: Chatbot Arena (Human Evaluation)[00:20:30] Chatbot Arena: Code Generation Evaluation[00:24:43] Evaluating LLMs: Beyond Chatbots and Truth[00:26:11] Exploring Evaluation Tools: Artificial Analysis (Quality, Speed, Price)[00:28:47] Exploring Evaluation Tools: Galileo (Hallucination Report)[00:31:16] Case Study: DeepSeek and the Importance of Contextual Evaluation[00:34:53] The Future of LLM Testing and Quality Assurance[00:37:49] Wrap Up contact information.#LLM #LargeLanguageModels #AIEvaluation #ProductManagement #TechTalk #TwoVoiceDevs #HuggingFace #GenAI #GenerativeAI #ChatbotArena #ArtificialAnalysis #Galileo #DeepSeek #ChatGPT #Gemini #Mistral #Claude #ModelSelection #AIdevelopment #SoftwareDevelopment #Testing #QA #RAG #MachineLearning #NLP #Coding #TechPodcast #YouTubeTech #Developers

Google's white paper on AI Agents has sparked debate – are they truly the next leap in AI, or just large language models dressed up with new terminology? Join Allen and Mark of Two Voice Devs as they dive into the details, exploring the potential of Google's framework while also critically examining its shortcomings. They analyze the core components of agents – models, tools, and orchestration – highlighting the value of defining tools as capable of taking actions. But they also raise key questions about the blurry line between models and agents, the confusing definitions of extensions and functions, and the critical omission of authentication and identity considerations. This episode is a balanced take on a fascinating and complex topic, offering developers valuable insights into the evolution of AI systems. Key Moments: [00:00:20] The core definition of agents: A promising start, or too broad? [00:05:08] Model vs. Orchestration: Understanding the decision-making layers. [00:17:33] "Tools" Unpacked: Exploring actions, extensions, and functions [00:25:14] The crucial gap: Authentication, Identity, and User context. [00:29:36] Reasoning techniques: React, Chain, and Tree of Thought explained. [00:35:41] The model-agent debate: Where is the boundary line? [00:37:45] Setting the stage for Gemini 2.0? [00:39:06] A valuable discussion starter, but with room to grow. Hashtags: #AIAgents #GoogleAI #LLM #GenerativeAI #AIInnovation #TechAnalysis #TwoVoiceDevs #AIDevelopment #AIArchitecture #SoftwareEngineering #DeveloperPodcast #GeminiAI #MachineLearning #DeepLearning #AITools #Authentication #TechDiscussion #BalancedTech

Join Allen Firstenberg as he welcomes Lee Mallon, a first-time guest host, for an in-depth discussion about the future of development, user experiences, and the exciting potential of AI-driven personalization! Lee shares his journey from coding on a Toshiba MX 128k to becoming CTO of Yalpop, a company reinventing learning through personalized experiences. This isn't just another AI hype-cast – it's a deep dive into how we can shift our mindset to truly put users at the center of our development process, leveraging new tech to create delightful and efficient experiences. Lee and Allen discuss everything from the limitations of current recommendation engines to the emerging potential of AI agents and just-in-time interfaces. This is a must-watch for any developer looking to stay ahead of the curve and build truly impactful applications. #AI #ArtificialIntelligence #GenAI #GenerativeAI #Personalization #UserExperience #UX #Development #WebDev #FutureOfTech #LLMs #LargeLanguageModels #AIagents #MachineLearning #SoftwareDevelopment #Programming #WebDevelopment #TwoVoiceDevs #Podcast #TechPodcast #Innovation #Code #Coding #Developer #TechTrends #UserCentricDesign #Web4 #NoCode #LowCode #DigitalTransformation

Hold onto your keyboards, folks! AI is shaking up the software engineering world, and in this electrifying episode of Two Voice Devs, Allen and Mark are diving headfirst into the chaos. We're not just talking about the theory – we're getting real about how AI coding tools are actually impacting developers right now. Is this the end of coding as we know it, or the dawn of a new era of software creation? More Info: * https://newsletter.pragmaticengineer.com/p/how-ai-will-change-software-engineering * https://addyo.substack.com/p/the-70-problem-hard-truths-about [00:00:00] Introduction: Meet Allen and Mark and hear about their busy start to the year. [00:00:39] The Trigger: Discover the article from The Pragmatic Engineer that sparked this conversation about the role of AI in software engineering. [00:02:16] Addressing the Panic: We discuss the common fear: is AI going to steal developer jobs? [00:03:34] Key Article Points: Allen breaks down the seven key areas of the article: how developers are using AI, the "70% Problem," and more. [00:04:43] Design Patterns & Craftsmanship: Mark discusses how AI-driven development relates to established software patterns and developer craftsmanship. [00:07:44] The Knowledge Paradox: Unpack the key difference in how senior and junior developers use AI and the potential issues it raises. [00:10:06] AI vs. Stack Overflow: We explore the differences between getting code from AI and from community platforms like Stack Overflow. [00:12:49] Personal Experiences: Allen and Mark share how they're actually using AI tools in their coding workflows. [00:17:09] AI Usage Patterns: Discussing the "constant conversation", "trust but verify", and "AI first draft" patterns. [00:20:55] The 70% Problem Revisited: Is AI just getting us part way there? [00:23:24] AI as a Team Member: Exploring the idea of AI as a pair programming partner and whether it's actually helping. [00:24:41] Trusting your Experience: the importance of listening to the gut feeling of an experienced developer when AI-generated code "feels" wrong. [00:26:06] Programming Languages are Easy for AI: The simplicity and consistency of programing grammars. [00:27:47] Is English the New Programming Language?: We debate the idea that natural language is becoming as important as coding and discuss what "programming" really means. [00:30:36] The Problem with Trying to Make Programming Easy: Historical attempts to make programming easier are revisited. [00:32:37] Programming vs the Rest of the Job: The core job of a software developer is more than just programming and writing code. [00:37:21] Quality & Craftsmanship in the Age of AI: We explore what will make software stand out in the future and how crafting great software still matters. [00:40:27] AI for Personal Software: Could AI drive a renaissance in personal software, similar to the spreadsheet? [00:42:53] The Importance of AI Literacy: Mastering AI development is the new skill to make developers even more valuable. [00:43:47] Closing Thoughts: The essential skills of developers remain crucial as we move into the future of AI driven coding. [00:44:59] Call to Action: We encourage you to join the conversation and share your thoughts on AI and software development. This isn't just another tech discussion – it's a high-stakes debate about the so ul of software engineering. Will AI become our greatest ally, or our ultimate replacement? Tune in to find out! #AIApocalypse #CodeRevolution #SoftwareEngineering #ArtificialIntelligence #Coding #Programming #Developers #TechPodcast #TwoVoiceDevs #MachineLearning #AICoding #FutureofCode #TechDebate #DeveloperSkills #CodeCraft #AIvsHuman #CodeNewbie #SeniorDev #JuniorDev #TechTrends

Join Mark and Allen, your favorite Two Voice Devs, as they explore the exciting (and sometimes frustrating!) world of Gemini 2.0's search grounding capabilities and how to use it with LangChainJS! Allen shares his recent holiday project: a deep dive into Google's latest AI tools, including the revamped search grounding feature, and how he made it work seamlessly across Gemini 1.5 and 2.0. We'll show you the code and demonstrate the differences between using search grounding and not, using real-world examples. Learn how to build your own powerful, grounded AI applications and stay ahead of the curve in the rapidly changing AI landscape! In this episode, you'll discover: [00:00:00] Introduction to Two Voice Devs and what we've been up to [00:00:24] Allen discusses tackling bug fixes and updates with Gemini 2.0 and LangChain [00:00:51] The new Gemini 2.0 Search Grounding Tool: what's new? What does it mean to be "agentic"? [00:02:13] Allen dives into the Google Search Tool, understanding the differences between 1.5 and 2.0, and building a layer for easy use in LangChain [00:03:06] Allen walks us through the code! The magic of setting up a model with or without search capabilities in LangChainJS [00:04:48] Using output parsers and annotating your results in LangChainJS [00:05:53] Similarities between Perplexity's results, and how LangChainJS handles output [00:06:46] Running the same query with and without grounding, and the dramatic difference in the response (Who won the Nobel Prize for Physics in 2024?) [00:08:26] A closer look at how LangChainJS presents its source references and how to use them in your projects. [00:12:55] Taking advantage of tools that Google is providing [00:13:20] The goal of keeping backward compatibility for developers [00:15:39] Exploring how this is a version of RAG and how that compares to using external data sources [00:16:50] What are data sources in VertexAI and how they relate? [00:19:14] What is the cost? How is Google pricing the search capability? [00:20:59] More to come soon from Allen with LangChainJS! Don't miss this deep dive into cutting-edge AI development! Like, subscribe, and share if you find this information helpful! #Gemini #LangChain #LangChainJS #AI #ArtificialIntelligence #GoogleAI #VertexAI #SearchGrounding #RAG #RetrievalAugmentedGeneration #LLM #LargeLanguageModels #OpenSource #TwoVoiceDevs #Programming #Coding #GoogleSearch #DataScience #MachineLearning #Innovation #TechPodcast #TechVideo

Happy New Year from Two Voice Devs! Join Allen Firstenberg and Mark Tucker as they recap the whirlwind that was 2024 in AI and tech, and make some bold predictions for 2025. We're diving deep into the biggest players, the most exciting innovations, and the developer challenges that lie ahead. From OpenAI's O3 and Google's Gemini 2.0 to the rise of Anthropic and the resurgence of head-mounted wearables, we preview the stories we'll be talking about this year. Plus, we discuss the important questions around the cost, both financial and environmental, of this new AI landscape. This episode is packed with insights for any developer looking to navigate the rapidly evolving world of artificial intelligence. Don't miss our discussion on what "agents" actually mean, and what the future holds for voice assistants. Timestamps: [00:00:00] Intro & Happy New Year! - Welcome to Two Voice Devs and a fun fact to kick things off! [00:01:14] Looking Back at 2024: A recap of the biggest AI movers of the past year. [00:01:32] OpenAI & Google Dominate: Analyzing the impact of OpenAI and Google's announcements, including O3, Gemini 2.0 Thinking, Sora, Veo, and Imagen. [00:04:02] OpenAI's Internal Turmoil and Google's Notebook LM: A look into the organizational chaos at OpenAI and the impressive upgrade of Notebook LM using Gemini 2.0. [00:05:24] Apple Intelligence, Amazon & the Catch-Up Game: Discussions around the progress of Apple and the challenges Amazon is facing, along with Anthropic. [00:08:15] Meta's LLAMA Models and Ray Bans: Exploring the surprising impact of Meta's AI models and the resurgence of head-mounted wearables. [00:10:04] Developer Realities: Fine-Tuned Models & DevOps: Mark discusses the importance of smaller, fine-tuned models and DevOps practices for language models. [00:11:54] The Environmental & Ethical Concerns of AI: A critical discussion about the environmental impact, ethical concerns, and privacy considerations of large language models. [00:13:15] Allen's 2024 Contributions: Langchain.js and GDE Presentations: Allen shares his work with open-source projects, LangChain, and traveling as a GDE [00:16:56] 2025: Predictions and "Agents": The focus is on the emergence of "agents" and the uncertainty surrounding their definition. [00:19:18] Defining "Agents": Allen lays out his predictions of what makes an agent. [00:20:58] The Resurgence of Voice Assistants: Discussing the future of voice assistants and the potential revival with the emergence of new technologies. [00:23:59] Google's Project Astra and Android XR: Exploring the new integrations in the voice and AI spaces. [00:24:46] Home Assistant: An Open Source Alternative: A deep dive into this lesser discussed project and it's voice hardware offering. [00:27:09] Amazon's Catch-Up: Is Amazon ready to get back into the AI and voice assistant game? [00:28:01] Looking forward into the future of LLMs: Predictions on LLMs and where they're going. [00:29:20] Outro: Thank you for joining Two Voice Devs. #AI #GenAI #ArtificialIntelligence #MachineLearning #LargeLanguageModels #LLM #OpenAI #Google #Gemini #Sora #Anthropic #Meta #LLAMA #AppleIntelligence #Amazon #Alexa #VoiceAssistant #Wearables #MetaRayBans #AndroidXR #GoogleGlass #Agents #Developer #Tech #Innovation #LangChain #GDE #TwoVoiceDevs #Podcast #YouTube #2024Recap #2025Predictions #TechTrends #Programming #Coding #OpenSource

It's the holiday season, and the AI world has been showering us with gifts! Join Mark and Allen on Two Voice Devs as they unwrap a mountain of new announcements and releases from Amazon, Meta, Google, and OpenAI. From groundbreaking new models to developer-friendly tools, this episode is packed with insights on the latest advancements in AI. We'll explore the features and potential of each new "present" and discuss what it means for you, the developer. [00:00:00] Intro and Holiday Greetings: Mark and Allen kick off the show, reflecting on the recent flurry of AI releases. [00:00:15] The AI Gift Giving Season: A lighthearted introduction on the sheer volume of new AI tools being released. [00:01:41] Amazon Nova Models: Amazon's surprising release of multiple new models, including Micro, Lite, and Pro, with a peek at Canvas (image generation) and Reel (video generation). [00:04:42] Meta's Llama 3.3: The focus on multilingual capabilities and open-source nature of Llama 3.3. [00:05:38] OpenAI vs. Google Announcement Showdown: The back-and-forth between Google and OpenAI with a focus on developer-related announcements. [00:06:40] Google's Imagen 3 & Veo: Google's new advancements in image and video generation available on Vertex AI, including image editing via prompting. [00:07:28] OpenAI's Sora Release: OpenAI makes their impressive video generation model available, but notably, not yet via API. [00:08:34] OpenAI's Canvas for Code: Explore how you can interact with code as a chatbot on a virtual canvas. [00:09:21] Microsoft's Expanded Copilot Free Tier: A note about Microsoft expanding access to their code tool. [00:09:38] Google's Jules: The AI Bug Detective: An introduction to Google's automated bug-fixing system which proposes fixes in a version control branch. [00:11:09] OpenAI's O1 Model: The official release of the O1 model with function calling, structured output, and image input capabilities. [00:11:42] Gemini 2.0 API: Google's improved Gemini API, now in public preview, offering better performance with optimized tools. [00:14:01] OpenAI's Real-Time API & WebRTC: Details about real time APIs, including WebRTC support for simplified browser-to-server connections. [00:16:15] Google's Gemini 2.0 Live API: Real-time streaming API using WebSockets for multimodal input and output, with demos available on AI Studio. [00:17:01] Google's New SDKs: A deep dive into the unified libraries for AI Studio and Vertex AI, simplifying things for developers. [00:18:10] OpenAI's new Java and Go Libraries: OpenAI ups their game by adding libraries to match Google's supported development platforms. [00:19:49] Google's PaliGemma 2 and Android XR: Vision-enabled open model, and a new Android platform for headsets and smart glasses. [00:22:04] Wrapping Up: Mark and Allen discuss which tools they're most excited about for the break and what's in store for the future. Let us know in the comments what you're most excited about, or if you noticed anything we missed. We'll discuss it on future episodes. #AI #ArtificialIntelligence #MachineLearning #GenerativeAI #LLM #LargeLanguageModels #AmazonNova #Llama3 #Gemini2 #OpenAI #GoogleAI #VertexAI #AIStudio #ChatGPT #GPT #O1 #Reasoning #ImageGeneration #VideoGeneration #DeveloperTools #Coding #Programming #WebRTC #AndroidXR #TechNews #TwoVoiceDevs

Ever felt like your tech presentations, tutorials, or even code explanations are falling flat? You're not alone! In this episode of Two Voice Devs, Allen and Mark dive deep into the art of effective communication in tech, exploring how to move beyond just listing facts to building a compelling narrative that actually helps people understand. Inspired by a recent presentation that Allen felt was "just okay," they tackle the challenge of how to present information in a way that resonates, whether you're on stage, creating content, or mentoring new developers. [00:00:00] Introduction to Two Voice Devs [00:00:16] End-of-year craziness and the inspiration for the episode [00:00:40] Allen's experience with a presentation that felt flat despite positive feedback. [00:01:31] The realization of a missing narrative in the presentation. [00:02:27] Discussion of building narrative into different types of content. [00:02:33] Deep dive into the structure and content of Allen's Gemini presentation. [00:04:04] The real message Allen was hoping to convey, and where the presentation fell short. [00:05:34] The importance of the "why" behind the "what" when presenting new features and concepts. [00:05:50] Exploring the concept of "telling a story" to make technical concepts easier to understand. [00:06:29] How individual learning experiences influence the way that you present material. [00:07:51] Balancing the desire to include all the information, while also keeping a succinct message. [00:08:50] Pivoting to talking about other ways of imparting information. [00:09:07] Mark's method of learning and creating diagrams, which then turn into a video. [00:11:08] The challenge of jumping into code without sufficient background. [00:12:10] Presenting information in the order that makes sense to you and why. [00:12:59] Learning by creating and being willing to share even when you are still learning. [00:13:39] Why committing to a presentation helps you learn a subject. [00:14:44] Using social media to get information out there quickly, and also, sample projects. [00:15:27] How starting with small chunks of code can help with understanding [00:16:31] Using AI tools to explain code. [00:17:13] How developers need to understand why code works, and not just that it works. [00:18:58] Why it's important to make learning a conversation and asking questions. [00:19:29] Mentoring and understanding where students are starting from. [00:20:54] How in-person feedback is both a benefit and a challenge. [00:22:12] Creating a safe space for collaborating and learning together. [00:23:38] Working together to get a level of understanding. [00:24:13] Call to action for audience to share their techniques. #TechContent #TechTutorials #DeveloperPresentations #Mentoring #SoftwareDevelopment #CodeTutorial #DevTips #TechNarrative #CommunicationSkills #TwoVoiceDevs #Coding #SoftwareEngineering #Teaching #Learning #AI #Gemini #Storytelling #MadeToStick #TechnicalCommunication #DevFest #Programming