Build 🏗️, Ship 🚢, and Share 🚀

EVENT RECAP 🧠 The Illusion of Thinking Last week, we examined The Illusion of Thinking, which argues that scaling up test-time compute does not work on problems of extremely high complexity. The response paper by Claude Opus, et al. "The Illusion of The Illusion of Thinking" argues the paper was contrived and poorly designed. Who is right, and wait, do LLMs think or not?? 🧑🏫 Slides 🎥 Recording COMING UP THIS WEEK Deep Research: The API OpenAI has officially released Deep Research through the...

EVENT RECAP 🦙 LlamaIndex Agent Memory: From Short-Term Storage to Intelligent Retention Last week, LlamaIndex DevRel Tuana Çelik and our very own Laura "The Legend" Funderburk explored in depth what it means to enable memory for agents, memory types 🧑🏫 Slides 🎥 Recording COMING UP THIS WEEK 🧠 Large Reasoning Models: The Illusion of Thinking On Wednesday July 2, we'll dive into the great “reasoning vs. mirage” debate as we put two headline-grabbing 2025 papers—Shojaee et al.’s “The Illusion of...

EVENT RECAP 🧰 Live from the Toronto Machine Learning Summit! Last week, our team met in person for the Machine Learning Summit in Toronto where Dr. Greg and The Wiz presented the workshop RAG, Agents, and MCP: The 2025 Best-Practice Stack, and also gave us their first-hand insights into conference talks at the Summit - plus, get to meet our team! 🎥 Recording 🦙 Llama Stack: Zero to Production Hero This week, our team explored Meta’s Llama Stack, Llama Guard, and the many ways we can think...

EVENT RECAP 🧰 A2A: Agent2Agent Protocol Last week, we learned about the Agent2Agent (A2A) protocol - how does the idea for A2A complement Model Context Protocol (MCP), and how can we use them with Agent Cards to get more out of our multi-agent apps? 🧑🏫 Slides 🧑💻Code 🎥 Recording COMING UP THIS WEEK Codex: The Autonomous SWE On Wednesday, June 11, at 10:00 AM PT, join us live as we investigate ChatGPT Codex, OpenAI’s first cloud-hosted Autonomous Software Engineer (A-SWE) that reads, edits,...

EVENT RECAP 🧰 Google ADK: Agent Development Kit Last week, we learned why Google waiting until many other agent orchestration frameworks might have given them a leg up in the core constructs they used in the Agents SDK. Spoiler alert: it's pretty good! 🧑🏫 Slides 🧑💻Code 🎥 Recording COMING UP THIS WEEK Building Agentic Systems with Protocols: MCP & Agent2Agents (A2A) Tomorrow at 2:00 PM PT, we're diving deep into protocols including both MCP and A2A! How should we think about building...

EVENT RECAP 🧰 AnyMCP: Deploying MCP Servers Last week, we learned to deploy MCP servers to APIs, we compared MCP servers to REST APIs, and heard from experts Abishek and Lucas about the future of leveraging MCP servers in production LLM applications. 🧑🏫 Concepts: AnyMCP 🎥 Recording: AnyMCP: Deploying MCP Servers COMING UP THIS WEEK Google ADK: Agent Development Kit Google's ADK, the Agent Development Kit, is a new agent framework that allows us to design, deploy, and evaluate intelligent...

Event Recap! 🧰 RAG: Production Best Practices Last week, we learned what enterprises must do with their infrastructure stack to maximize development velocity, including how to leverage the right amount of on-prem and cloud tools! 🧑🏫 Concepts: Enterprise RAG 🧑💻 Code: On-Prem RAG Repo 🎥 Recording: The 2025 Best-Practice RAG Stack, Part II Coming Up This Week! AnyMCP: Deploying MCP Servers Our friends at Arcee just released AnyMCP, and it's built to easily manage your Model Context Protocol...

👨💻 Do you code everyday? Do you want to code everyday? 💼 Do you manage people who code every day? Vibe coding is not enough. A vibe coder will never take your job. Vibe coders will not make the engineers on your team obsolete. But AI-Assisted Developers will. If you're not doing AI-assisted development yet, start here👇 to 🏗️ build, 🚢 ship, and 🚀 share your first LLM application with the latest 2025 best-practice tool stack! Take The AI Engineer Challenge Today Step 1: Set up your AI IDE Step...

Hey, AI Makerspace community! Want to build and deploy your first LLM application? The best place to start is to join us live tomorrow for The 2025 AI Engineer Challenge at 10 AM PDT. We will provide a detailed hands-on walkthrough of the tools, stack, and skills you’ll need to go from zero to AI Engineer hero and to start building end-to-end today! 🔍 Coming Up RAG: The 2025 Best-Practice Stack, Part II: Enterprise Production Part II of our RAG series dives into the real-world blockers to...