Transcripts
These pages expose cached YouTube and livestream transcripts as linkable wiki markdown. They are generated from local transcript caches and should be regenerated whenever new transcripts are imported.
Transcript Pages
- Transcript: 20 days of compute vs 7 hours: rethinking what state-of-the-art means — Bertrand Charpentier, Pruna
- Transcript: 2026 AI Engineer Vibe Reel
- Transcript: 4Sx He5C4Si
- Transcript: 500 people vibe-coded for 30 days. I was one of them. - Sanja Grbic, Automattic
- Transcript: 6 Things to Know about AIE World's Fair 2026
- Transcript: A Genius With Amnesia - Victor Savkin, Nx
- Transcript: Agents Building Agents - Alfonso Graziano, Nearform
- Transcript: Agents in Production: How OpenGov Built and Scaled OG Assist - Gabe De Mesa, OpenGov
- Transcript: AI System Design: From Idea to Production - Apoorva Joshi, MongoDB
- Transcript: AI-Driven Multi-Document Correlation for Financial Compliance - Varsha Shah, Independent
- Transcript: Analyzing 10,000 Sales Calls With AI In 2 Weeks — Charlie Guo
- Transcript: BDD, ADR, PRD, WTF: Capturing Decisions for Humans and AI Alike — Michal Cichra, Safe Intelligence
- Transcript: Benchmarking semantic code retrieval on Claude Code — Kuba Rogut, Turbopuffer
- Transcript: Beyond Components: Designing Generative UI for MCP Apps — Ruben Casas, Postman
- Transcript: Beyond the Harness: A Journey Towards Adaptative Engineering - Rajiv Chandegra, Annicha Labs
- Transcript: Beyond Transcription: Building Voice AI That Understands Conversations — Hervé Bredin, pyannoteAI
- Transcript: Browser Agents Don't Need Better Models. They Need Better Eyes. - Kushan Raj, ARK
- Transcript: Build AI Systems for Discernment, Not Approval - Angel Ortmann Lee, Duolingo
- Transcript: Build Systems, Not Code - Angie Jones, Agentic AI Foundation
- Transcript: Building Agent Interfaces: Lessons from Chrome DevTools (MCP) for Agents — Michael Hablich, Google
- Transcript: Building Agents with Amazon Nova Act and MCP - Du'An Lightfoot, Amazon (Full Workshop)
- Transcript: Building an ACP-Compatible Agent Live — Bennet Fenner, Zed
- Transcript: Building an Autonomous Engineering Org - Angie Jones, Agentic AI Foundation
- Transcript: Building Great Agent Skills: The Missing Manual
- Transcript: Building Interactive UIs in VS Code with MCP Apps — Marlene Mhangami & Liam Hampton, GitHub
- Transcript: Building safe Payment Infrastructure for the autonomous economy — Steve Kaliski, Stripe
- Transcript: Bypassing the Multimodal Tax: Hybrid RAG, SQL RRF & UI Telemetry - Abed Matini, Ogilvy
- Transcript: Continual Learning for AI Agents: From Failures to Durable Improvements - Soheil Feizi, RELAI
- Transcript: Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff — Vincent Koc, OpenClaw
- Transcript: Evals 101 — Doug Guthrie, Braintrust
- Transcript: Evals Are Broken, Use Them Anyway — Ara Khan, Cline
- Transcript: Field Guide to Fable — Thariq Shihipar, Anthropic
- Transcript: Frontier results, on device - RL Nabors, Arize
- Transcript: GPU Cloud Deployment Without Leaving Your IDE — Audry Hsu, RunPod
- Transcript: GTM Is You - Victoria Melnikova, Evil Martians
- Transcript: How Lovable self-improves every hour — Benjamin Verbeek, Lovable
- Transcript: How to talk to statues — Joe Reeve, ElevenLabs
- Transcript: How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI
- Transcript: Htm02Kmnznk
- Transcript: HTML is All You Need (for Agents to Make Graphics) - Amol Kapoor, Nori
- Transcript: I Run a Fleet of AI Agents Across Three Machines. Here's What Broke. - Kyle Jaejun Lee, KRAFTON
- Transcript: I2Cbiws9J10
- Transcript: MCP Apps: Primitives, discovery, and the Future of Software - Pietro Zullo, Manufact, Inc
- Transcript: MCP UI: Extending the frontier — Liad Yosef and Ido Salomon, MCP Apps
- Transcript: OpenClaw in Your Hand: Building a Physical AI Terminal - Lech Kalinowski, Callstack
- Transcript: Production Evals For Agentic AI Systems - Nishant Gupta, Meta Superintelligence Labs
- Transcript: RAG is dead, right?? — Kuba Rogut, Turbopuffer
- Transcript: Recursive Coding Agents - Raymond Weitekamp, OpenProse
- Transcript: Research to Reality: Bringing Frontier ML Research to Production - Vaidas Razgaitis, Higharc
- Transcript: Respect The Process - Andrew Dumit, Watershed Technology Inc.
- Transcript: Road to 5 Million Tokens: Breaking Barriers in Long Context Training — Max Ryabinin, Together AI
- Transcript: Running a Chess YouTube Channel entirely by AI — Stephan Steinfurt, TNG
- Transcript: Self Driving Products: Product Signals to Pull Requests — Joshua Snyder, PostHog
- Transcript: Ship Real Agents: Hands-On Evals for Agentic Applications — Laurie Voss, Arize
- Transcript: Shipping Production AI Inside Government — William Tarr, Ministry of Justice (DO NOT PUBLISH)
- Transcript: Sovereign Escape Velocity: Ownership w Open Models — Gus Martins, & Ian Ballantyne, Google DeepMind
- Transcript: Stop Making Models Bigger, Make Them Behave — Kobie Crawford, Snorkel
- Transcript: Stop Writing Tone Instructions. Layer Them. - Isadora Martin-Dye, Isadora & Co
- Transcript: Structuring the Unstructured - Cedric Clyburn, Red Hat
- Transcript: SWE-Marathon: Evaluating Coding Agents at Billion-Token Scale - Rishi Desai, Abundant AI
- Transcript: SWE-rebench: Lessons from Evaluating Coding Agents — Ibragim Badertdinov, Nebius
- Transcript: Task Fidelity Scaling Laws — Kobie Crawdord, Snorkel
- Transcript: Teaching Coding Agents to do Spreadsheets - Nuno Campos, Witan Labs
- Transcript: Text Diffusion — Brendan O’Donoghue, Google DeepMind
- Transcript: The 100-Tool Agent Is a Trap - Sohail Shaikh & Ankush Rastogi, Prosodica
- Transcript: The agent-ready web: Simplify user actions with WebMCP — Tara Agyemang, Google
- Transcript: The Agentic AI Engineer - Benedikt Sanftl, Mutagent
- Transcript: The Art & Science of Benchmarking Agents — Vincent Chen, Snorkel AI
- Transcript: The Future Is Domain-Specific Agents - Justin Schroeder, StandardAgents
- Transcript: The Log Is The Agent - Ishaan Sehgal, Omnara
- Transcript: The Miranda Hypothesis: How Hamilton Poisoned Persona Evals - Jacob E. Thomas, Results Gen
- Transcript: The Missing Layer After Launch - Raphael Kalandadze, Wandero AI
- Transcript: The Pipeline Is Dead - Iris ten Teije, Sky Valley Ambient Computing
- Transcript: The Prompt Is Still a Punch Card - Ted Johnson, JoinIn AI
- Transcript: The Prompt is the Platform - Dominik Tornow, Resonate HQ
- Transcript: Think You Can Build a Game with AI? Think Again! - Danielle An & David Hoe, Meta
- Transcript: Under 5 minutes to a deployed LLM endpoint — Audry Hsu, RunPod
- Transcript: User Signal Dies at the Retrieval Boundary - Sonam Pankaj, StarlightSearch
- Transcript: Using RL Agent to Detect and Remediate ETL Pipeline Failures - Anna Marie Benzon
- Transcript: Using Spec-Driven Development for Production Workflows - Erik Hanchett, AWS
- Transcript: Voice In, Visuals Out: The Agony and the Ecstasy - Allen Pike, Forestwalk Labs
- Transcript: We Cut 94% of AI Coding Tokens With a Local Code Index - Rajkumar Sakthivel, Tesco
- Transcript: What do we build now? — @t3dotgg
- Transcript: What if the harness mattered more than the model? - Aditya Bhargava, Etsy
- Transcript: What Lies Beneath the API — Benjamin Cowen, Modal
- Transcript: When All Context Matters: Extended Cache Augmented Generation - Luis Romero-Sevilla, Orbis
- Transcript: Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carey, Cloudflare
- Transcript: Why MCP and ChatGPT Apps Use Double Iframes — Frédéric Barthelet, Alpic
- Transcript: Why More Context Makes Your Agent Dumber and What to Do About It — Nupur Sharma, Qodo
- Transcript: Why Self-Driving Production Is the Future — Eric Schwartz, Traversal | AI Engineer World's Fair 2026
- Transcript: Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j
- Transcript: You Can't Prompt the Room: The Last Skill AI Won't Replace - Balázs Horváth, VisualLabs
- Transcript: You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia
- Transcript: Your agent is blindfolded — Johan Lajili, Poolside AI
- Transcript: Your Agent Is Wasting Tokens and You Don't Know It - Erik Hanchett, AWS
- Transcript: Your Agent's Biggest Lie: "I Searched the Web" — Rafael Levi, Bright Data
- Transcript: Your AI Product Will Fail Unless You Can Explain It - Veronica Hylak, Hey AI
- Transcript: Your coding agent doesn't always follow your rules — Talha Sheikh, Checkout.com
- Transcript: Your LLM Deception Monitor Is Broken. The Fix Is in the Training Data - Sachin Kumar, LexisNexis
- Transcript: £85K Burned on a Failed PoC: What Actually Gets Agents to Production — Sandipan Bhaumik, Databricks