Two Voice Devs

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 Benchmarking

05:08 Policy & Societal Benchmarking (Preventing Harms)

07:55 The Need for Diverse Benchmarking Teams

09:55 Technical Aspects & Tooling (Data Integrity, Versioning)

10:50 Prompt Engineering & Versioning for Benchmarking

12:48 Preventing Models from Tuning to Benchmarks

15:30 Prompt Template Engines & Generating Prompts

17:10 Other Benchmarking Tools & Testing Nuances

19:10 Benchmarking Compared to Traditional QA

21:45 Evaluating Benchmark Results (Human & Metrics)

23:05 The Challenge of Establishing an Evaluation Scale

23:58 How to Get Started in Benchmarking (Volunteering, Organizations)

25:20 Open Benchmarks & Where to Find Them

26:35 Benchmarking Your Own Model or App

28:55 Why Benchmarking Matters for App Builders

29:55 Where to Learn More & Follow Amy

Hashtags:

#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-developers

Timestamps:

00:49 - Ankur's Role as Global Head of Cloud Advocacy

01:48 - The Bi-directional Nature of Developer Relations

02:34 - Ankur's Journey into Tech and DevRel

09:47 - 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 GDE

18:24 - Riding the Waves of Technological Change (AI, Vibe Coding)

20:37 - The Importance of Understanding Abstraction Layers

25:41 - How Developers Can Engage with the DevRel Bridge

30:50 - 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-up

00:00:31 Welcome to Google Cloud Next 2025

00:01:18 Meet Alice Keeler: Math Teacher, GDE, and App Script Developer

00:03:44 App Script: Accessible Development & Real-World Solutions

00:05:40 Cloud Next 2025 Day 1 Keynote Highlights

00:06:18 New Generative AI Models: Veo (Video), Chirp 3 (Audio), Lyric (Sound), Imagen Updates

00:09:00 The Sphere Experience & DeepMind's Wizard of Oz AI Enhancement

00:14:00 From Hollywood Magic to Public Tools: Vertex AI Capabilities

00:16:30 Agent Builder: The Future of AI Agents & Accessible Development

00:23:37 Agent to Agent Protocol: Enabling Complex AI Workflows

00:25:20 Other Developer News: AI Studio Revamp & Gemini 2.0 Live API

00:26:30 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 episode

01:20 Reconsidering MCP's purpose and metaphors

03:25 Practical challenges with clients (like Claude Desktop) and configuration

05:00 Discussing future AI interfaces and app integration

09:15 Understanding Local vs. Remote MCP servers and hosting models

12:10 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 tool

23:50 Code walkthrough: Defining tools, resources, and prompts

31:15 Exploring remote (HTTP) connection options in the Inspector

32:30 Introducing Smithery.ai as a potential MCP registry

33:45 Navigating the Smithery registry and encountering configuration confusion

36:15 Analyzing server source code vs. registry listings - Highlighting discrepancies

44:30 Reflecting on the current practical usability and complexity of MCP

46:10 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 UI

0:03:20 Demonstrating Generative UI Pitfalls with a Smart Home Dashboard

0:05:15 Dynamic Adaptation and User Intent

0:11:30 Accessibility and Customization in Generative UI

0:13:30 Encountering Limitations and the Need for Fine-Tuning

0:17:50 Introducing Fine-Tuning for LLMs: Adapting Pre-trained Models

0:19:30 Fine-Tuning for New Patterns and Domain-Specific Understanding

0:20:50 The Role of Training Data in Supervised Fine-Tuning

0:23:30 Generalization of Patterns by LLMs

0:24:20 Exploring Key Fine-Tuning Hyperparameters: Learning Rate and Training Epochs

0:30:30 Demystifying Supervised Fine-Tuning and its Benefits

0:33:30 Saving and Hosting Fine-Tuned Models: Hugging Face and Google Cloud Run

0:36:50 Integrating Fine-Tuned Models into Applications

0:38:50 The Model is Not the Product: Focus on User Value

0:39:40 Closing Remarks and Teasing Future Discussions on Monitoring

Hashtags:

#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 AI

00:02:00 - Defining Generative UI and distinguishing it from AI-aided design

00:03:30 - Exploring potential examples of Generative UI based on user needs and context

00:04:45 - The difference between traditional static UIs and dynamic generative UIs

00:06:45 - How LLMs can be leveraged for real-time UI generation

00:07:15 - The overlap and distinction between Generative UI and Conversational

UI

00:08:30 - Challenges of Generative UI: Predictability and guiding users

00:09:30 - The importance of maintaining established UX patterns in Generative UI

00:12:30 - Traditional UI limitations and the promise of personalized generative UIs

00:14:00 - Context-specific information access and adapting to user roles

00:15:30 - An example of Generative UI in a business intelligence dashboard

00:17:00 - A six-stage pipeline for how Generative UI systems might work

00:19:00 - The concept of "agents on rails" in the context of UI generation

00:20:30 - The reasoning and tool-calling aspects of generative UI agents

00:22:30 - Tools as the core of UI generation and component recognition challenges

00:24:30 - Demonstrating the dynamic generation of UI components (charts)

00:27:30 - Exploring interactions and limitations of the generative UI demo

00:29:15 - The "hallucination" of UI components and the need for fine-tuning

00:31:30 - 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 buzz

1:06 Unveiling DeepSeek's Two Key Models

2:59 Understanding the Power of Attention

4:12 What is the latent space?

5:55 The nail salon example: Multi-Head Attention Explained

10:02 The doctor/cook/police analogy: Mixture of Experts Explained

13:51 AI vs. AI: DeepSeek's Cost-Saving Training Method

16:01 Hallucinations: Is AI Training Too Risky?

20:59 What are Reasoning Models and Why Do They Matter?

26:53 LLMs are pattern systems explained

28:22 How DeepSeek is using old GPUs

32:53 OpenAI vs. DeepSeek: The Data Plagiarism Debate

39:32 Political Correctness: The Challenge of Guardrails in AI

42:16 Why Open Source is Crucial for the Future of AI

43:20 Run DeepSeek locally on OLAMA

43:56 Final Thoughts

Hashtags: #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-blog

Timestamps:

0:00:00 Introduction

0:01:00 Alexa Plus Overview

0:02:00 Pricing & Classic Skills

0:05:00 Access & Availability

0:06:00 Alexa AI SDKs

0:12:00 Action SDK

0:21:00 WebAction SDK

0:27:00 Multi-Agent SDK

0:31:00 Big Questions for Developers

0:36:00 Will Alexa Be Fun Again?

0:41:00 Response Times & Notifications

0:45:00 Multimodal Experiences

0:46:00 Conclusion

#Alexa #AlexaPlus #VoiceDevelopment #AI #LLM #Amazon #Skills #VoiceFirst #Podcast #Developer #Tech #ArtificialIntelligence #TTS #ASR # ConversationalAI