Generated by All in One SEO v4.9.2, this is an llms.txt file, used by LLMs to index the site. # The Full Stop Thought Talking tech stuff (and not)... ## Sitemaps - [XML Sitemap](https://davidvonthenen.com/sitemap.xml): Contains all public & indexable URLs for this website. ## Posts - [Hybrid RAG in the Real World: Graphs, BM25, and the End of Black-Box Retrieval](https://davidvonthenen.com/2026/01/07/hybrid-rag-in-the-real-world-graphs-bm25-and-the-end-of-black-box-retrieval/) - If you've been building RAG systems and something feels off, this post explains why. It picks up where earlier discussions left off and looks at what happens when retrieval stops being something you can inspect or control. The focus is on how teams actually guide AI answers in practice, not by adding more embeddings, but - [DocumentRAG Using OpenSearch: GraphRAG-like Structure Without the Graph Overhead](https://davidvonthenen.com/2025/11/24/documentrag-using-opensearch-graphrag-like-structure-without-the-graph-overhead/) - The rise of GraphRAG has shown how important structure is for building reliable AI systems, but many teams run into the heavy lift of managing a full graph ontology or data representation. The BM25-based Document RAG Agent offers a middle ground. It keeps the clarity and grounding that people like in GraphRAG, but without the - [When AI Gets Real: Takeaways from a Week at Devoxx Morocco](https://davidvonthenen.com/2025/11/19/when-ai-gets-real-takeaways-from-a-week-at-devoxx-morocco/) - Devoxx Morocco brought together a mix of engineers, architects, and AI practitioners who were focused on the practical side of AI. The conversations were grounded in real problems rather than vague theory. People wanted to talk through design decisions, past failures, and the parts of their stack that still worry them. That set the tone - [Doing More with Less: The Quiet Revolution Powering AI Through IoT and Edge](https://davidvonthenen.com/2025/10/12/doing-more-with-less-the-quiet-revolution-powering-ai-through-iot-and-edge/) - Edge AI is quietly changing how we think about machine learning deployment. Instead of running models in the cloud, intelligence is moving closer to where data is created—on sensors, gateways, and even microcontrollers. This shift isn't about shrinking models for fun; it's about making AI useful where latency, bandwidth, and power all matter. In this - [Rethinking RAG: Building Smarter AI Agents with Agent2Agent and MCP](https://davidvonthenen.com/2025/09/22/rethinking-rag-building-smarter-ai-agents-with-agent2agent-and-mcp/) - RAG has been the go-to pattern for making AI smarter, but the way we build and think about agents is changing fast. At ODSC AI West, I'll be leading a workshop on how Agent2Agent and the Model Context Protocol (MCP) shift the conversation from retrieval-first to capability-first. Think of it as moving from giant, monolithic - [Invisible by Design: Context-Aware Interfaces that Assemble Themselves](https://davidvonthenen.com/2025/09/10/invisible-by-design-context-aware-interfaces-that-assemble-themselves/) - UI design is hitting a weird but exciting pivot. Static screens and fixed navigation are giving way to adaptive interfaces that come together in real time... driven by what you're doing, what you like, and where you are. In my RenderATL session, The Future of UI/UX: AI-Generated Interfaces Tailored Just-in-Time, I framed this as Just-in-Time - [Compliance-Ready AI: Provenance, Lineage, and Policy You Can Prove](https://davidvonthenen.com/2025/09/07/compliance-ready-ai-provenance-lineage-and-policy-you-can-prove/) - We’ve all heard the phrase "treat infrastructure as code," but what if I told you it's time to give your datasets the same respect? In AI and machine learning, tiny shifts in data ripple through models, causing unpredictable behavior that can lead to compliance nightmares. Our latest blog explores a fundamental shift in mindset—treating data - [From "Trust Me" to "Prove It": Why Enterprises Need Graph RAG](https://davidvonthenen.com/2025/08/20/from-trust-me-to-prove-it-why-enterprises-need-graph-rag/) - Enterprises don't need more "vibes-based" answers… they need receipts. Vector-only RAG is great at finding passages that feel right, but when auditors ask who said what, when, and why, cosine similarity can't testify. If your world runs on policies, provenance, and repeatability, you can't ship a black box and call it a day. Graph-based RAG - [NVIDIA GTC CFP Speaking Session Analysis: Emphasizing Solutions Over “Things”](https://davidvonthenen.com/2025/07/03/nvidia-gtc-cfp-speaking-session-analysis-emphasizing-solutions-over-things/) - NVIDIA's GPU Technology Conference (GTC) just wrapped up in Paris, and GTC is often dubbed the "Super Bowl of AI". I was fortunate enough to speak virtually on the topic of Explainable AI and attend the North American version in San Jose this year. I was impressed by the quality of the sessions and the - [Pushing the Boundaries: My Experience at the Real Time Communication Conference at Illinois Institute of Technology](https://davidvonthenen.com/2024/06/15/2023-real-time-communication-conference-3/) - This was my first time at the RTC Conference at Illinois Institute of Technology in Chicago, and I was blown away by the caliber of talks at the event. They ranged from very academic and theoretical to extremely practical, capturing what is happening on the ground today in real-time communications. The mix of attendees was - [Top Reasons to Mark Your Calendar for SCaLE Next Year](https://davidvonthenen.com/2024/06/15/top-reasons-to-mark-your-calendar-for-scale-next-year-2/) - In March, I had the fortune of attending and speaking at one of my favorite conferences, Southern California Linux Expo (SCaLE) 21x. As the name suggests, this is the 21st iteration of this tech-heavy yet family-oriented event, which usually takes place in Pasadena but, in some years, in the greater Los Angeles area. This is - [Machine Learning for Good: Training Models for Medical Analysis](https://davidvonthenen.com/2024/09/22/machine-learning-for-good-training-models-for-medical-analysis/) - The intersection of machine learning (ML) and Healthcare is not just a technological revolution—it's a profound shift in how we understand and approach human well-being. ML is a tool that's been evolving quietly behind the scenes for years, but its recent surge in healthcare applications feels like a leap into the future. From diagnostic imaging - [Mining Conversations: Building NLP Models to Decode the Digital Chatter](https://davidvonthenen.com/2024/09/25/mining-conversations-building-nlp-models-to-decode-the-digital-chatter/) - The world has gone digital, and so have our conversations. With over 1.5 billion messages sent weekly on Slack, 300 million daily virtual meetings on Zoom at its peak, and millions of interactions across Facebook, TikTok, and other platforms, the volume of conversation data is staggering. These conversations hold valuable insights, from trend detection to - [Unlocking Conversations: Hands-On NLP for Real-World Data Mining](https://davidvonthenen.com/2024/10/13/unlocking-conversations-hands-on-nlp-for-real-world-data-mining/) - Hey there, tech enthusiasts! I'm thrilled to share that I'll be hosting an exciting workshop at the upcoming Open Data Science Conference (ODSC). Titled “Building Multiple Natural Language Processing Models to Work in Concert Together”, this workshop will give you a practical, hands-on approach to creating and orchestrating NLP models. It's not just another "hello - [2024 RTC Conference Recap: Shining a Spotlight on AI in Healthcare and Voice AI Assistants](https://davidvonthenen.com/2024/10/16/2024-rtc-conference-recap-shining-a-spotlight-on-ai-in-healthcare-and-voice-ai-assistants/) - The 2024 Real Time Communication Conference at Illinois Tech was an electrifying event, showcasing emerging technologies across Voice, WebRTC, IoT/Edge, and groundbreaking research. But if you ask me, the real magic happens in the conversations between sessions. These impromptu chats with attendees always spark new ideas, collaborations, and insights that you won't find on any - [Will AI Replace Mid-Level Engineers by 2025? Not So Fast, Mark Zuckerberg](https://davidvonthenen.com/2025/01/17/will-ai-replace-mid-level-engineers-by-2025-not-so-fast-mark-zuckerberg/) - It's hard to ignore the growing buzz around artificial intelligence (AI) and its potential impact on various industries. Recently, Mark Zuckerberg predicted on Joe Rogan's podcast that AI could replace mid-level engineers by 2025. While it's a compelling narrative, it misses the mark for several reasons. Let's unpack why this prediction is more hype than - [Beyond the Resume: Speculative Hiring Trends in an AI World](https://davidvonthenen.com/2025/01/30/beyond-the-resume-speculative-hiring-trends-in-an-ai-world/) - I was recently at a conference where I started chatting with a computer science graduate about job hunting in the world today. We discussed the job market landscape as it exists today and all of the economic influences, disruptive technology (cough, AI, cough), and competition out there. When I first jumped into my first professional - [Rethinking Jobs When AI Does the Thinking: The Human Jobs AI Can’t Touch](https://davidvonthenen.com/2025/04/22/rethinking-jobs-when-ai-does-the-thinking-the-human-jobs-ai-cant-touch/) - AI isn't just coming... It's already here, and it's reshaping how we think about jobs. But the big question isn't about which jobs AI will take; it's about what new types of jobs humans will step into. We are transitioning from a knowledge-based economy to one driven by critical thinking and creative problem-solving. Soon, accessing - [Voice Cloning: The Text-to-Speech Feature You Never Knew You Needed And Why It Matters](https://davidvonthenen.com/2025/01/05/voice-cloning-the-text-to-speech-feature-you-never-knew-you-needed-and-why-it-matters/) - Over the holiday break, I started experimenting with cloning my voice for reasons I will get to later in this blog post. As I walked down the list of Voice Cloning providers out there and began to evaluate them using my cost-to-benefit ratio scale, a set of requirements and must-have capabilities emerged. In this blog - [YAKB: Running Kubernetes on Your Laptop](https://davidvonthenen.com/2018/10/22/yakb-running-kubernetes-on-your-laptop/) - Hi there! Yes, it's been a while since I have posted to my personal blog. Before I get to my post, I thought I would just bring you up to speed with what's been going on in my world since my last post. So I no longer work at Dell EMC. I also no longer - [ScaleIO: Deep Dive on Imperative Deployment](https://davidvonthenen.com/2017/01/18/scaleio-deep-dive-on-imperative-deployment/) - By now you probably have read the blog post, ScaleIO Framework v0.3: Deploy This!, where we announced the new version of the ScaleIO Framework. (If you haven't, I would definitely go check it out first.) In that release, a new feature called Imperative Deployment was unveiled which is the first structured method for deploying ScaleIO - [Dell EMC World 2017 – Las Vegas, NV](https://davidvonthenen.com/2017/05/04/dell-emc-world-2017-las-vegas-nv/) - It looks like that time of year again as we are just days away from Dell EMC World 2017. The {code} team will once again be in attendance and presenting some interesting sessions (16 in total), a Hands-On Lab (ran through it myself and it's great!), and various materials at the show. The buffet (Yes, - [Applications that Fix Themselves](https://davidvonthenen.com/2017/03/03/applications-that-fix-themselves/) - I know that in my last blog post I said I would be talking (and probably announcing) the FaultSet functionality planned for the next release of the ScaleIO Framework. As all things in the world of technology and software, things don't always go as planned. So today I am here to talk about some stuff - [mesos-module-dvdi Installation Walkthrough](https://davidvonthenen.com/2016/03/08/mesos-module-dvdi-installation-walkthrough/) - As other people in the EMC {code} team started getting involved with Apache Mesos, I have been helping by fielding questions and troubleshooting installations of both Mesos and mesos-module-dvdi so that others can kick the tires and become subject matter experts. It was brought to my attention that a good clean walkthrough of adding external - [Looking Back at SCaLE x14](https://davidvonthenen.com/2016/02/02/looking-back-at-scale-x14/) - For those that don't know what SCaLE is... SCaLE stands for the Southern California Linux Expo and this marked the 14th year the conference has been held which happened to be in Pasadena, CA on Jan 21-24. This was the first time I have attended SCaLE and I have to say that it was quite - [Looking Back at EMC World 2016](https://davidvonthenen.com/2016/05/17/looking-back-at-emc-world-2016/) - Wow! How quickly a week can go by. Like many of you, EMC World 2016 was my first time in attendance and it also happen to be the first time I have been given the opportunity to be a presenter for a larger audience. I though the experience exceeded my expectations and based on some - [LinuxCon ContainerCon Japan: Extended Edition](https://davidvonthenen.com/2016/07/20/linuxcon-containercon-japan-extended/) - My recap of LinuxCon ContainerCon Japan just went live on the EMC {code} Blog and it talks about some of the things that happened at the conference as well as talks about some key takeaways. I definitely encourage you to go and take a look at the article. This happens to be my first blog - [Oct Recap: It’s Been a Trip](https://davidvonthenen.com/2016/10/25/its-been-a-trip/) - I have recently been doing a lot of travel for work. I know that for some, this amount of travel is routine, but for myself, it has been pretty awesome. In the month of October, I have visited 2 places I have never been to before. But before I start with the picture show and - [Getting Ready for EMC World 2016](https://davidvonthenen.com/2016/04/19/getting-ready-for-emc-world-2016/) - We are getting closer and closer to EMC World 2016. I have to admit, its approaching crazy fast. This will be my first time attending EMC World. Seems odd saying that as I have attended many conferences in my career, but never the one my company throws. This time its going to be a different - [Enabling External Storage on Mesos Frameworks](https://davidvonthenen.com/2016/02/16/enabling-external-storage-on-mesos-frameworks/) - There has been a huge push to take containers to the next level by twisting them to do much more. So much more in fact that many are starting to use them in ways that were never originally intended and even going against the founding principles of containers. The most noteworthy principle of containers being - [Difficulties with Multi-Version Mesos Support](https://davidvonthenen.com/2016/01/19/difficulties-with-multi-version-mesos-support/) - I have been working with Apache Mesos for some time now and after a recent meeting with the Mesosphere team (the company largely driving the roadmap and development effort), I have come to learn that some Mesos users sit on the bleeding edge of releases and others that are sensitive to things like security, change - [Who is David vonThenen?](https://davidvonthenen.com/2015/12/30/who-is-david-vonthenen/) - Hi! My name is David vonThenen. I am a Developer Advocate with EMC {code}. Yes, that EMC that makes all the storage products we have all come to know and love. I have recently been given the opportunity to join a fairly new group, the {code} team, within EMC that lives and breathes Open Source - [Top Reasons to Mark Your Calendar for SCaLE Next Year](https://davidvonthenen.com/2024/06/15/top-reasons-to-mark-your-calendar-for-scale-next-year/) - In March, I had the fortune of attending and speaking at one of my favorite conferences, Southern California Linux Expo (SCaLE) 21x. As the name suggests, this is the 21st iteration of this tech-heavy yet family-oriented event, which usually takes place in Pasadena but, in some years, in the greater Los Angeles area. This is - [Pushing the Boundaries: My Experience at the Real Time Communication Conference at Illinois Institute of Technology](https://davidvonthenen.com/2024/06/15/2023-real-time-communication-conference/) - This was my first time at the RTC Conference at Illinois Institute of Technology in Chicago, and I was blown away by the caliber of talks at the event. They ranged from very academic and theoretical to extremely practical, capturing what is happening on the ground today in real-time communications. The mix of attendees was - [Pushing the Boundaries: My Experience at the Real Time Communication Conference at Illinois Institute of Technology](https://davidvonthenen.com/2023/10/16/2023-real-time-communication-conference-2/) - This was my first time at the RTC Conference at Illinois Institute of Technology in Chicago, and I was blown away by the caliber of talks at the event. They ranged from very academic and theoretical to extremely practical, capturing what is happening on the ground today in real-time communications. The mix of attendees was - [Let’s have a Conversation!](https://davidvonthenen.com/2022/08/29/lets-have-a-conversation/) - Hello! How are you doing? It’s been a while since we last chatted. Since you’re stopping by, you might notice immediately that I revived my blog (obviously). I took a break from it for a good couple of years while COVID did its thing; it made sense since we were locked indoors, unable to attend ## Pages - [Talks](https://davidvonthenen.com/talks/) - 2026 The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend - WeAreDevelopers World Congress (EU), June 2026 The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend - NDC Copenhagen, June 2026 Less Compute, More Impact: How Model Quantization Fuels the Next - [Resume](https://davidvonthenen.com/resume/) - David vonThenen AI/ML Engineer | Keynote Speaker | Building Scalable ML Architectures & AI Solutions | Python, Go, C++ E-mail: davidvonthenen [ at ] gmail.com / LinkTree: linktr.ee/davidvonthenen Summary As an AI/ML engineer and developer advocate, I thrive at the intersection of real-world engineering and developer empowerment. My career has been defined by architecting AI - [About Me](https://davidvonthenen.com/about-me/) - Konbanwa! 👋 I'm David vonThenen, a seasoned Lead Engineer, Evangelist, and Educator specializing in AI, Machine Learning, cloud-native architectures, storage, and networking. Currently, I'm a key player at Deepgram, where I lead initiatives to enhance platform adoption and drive growth through software and strategic community engagement. With over two decades of experience, I've had the ## Categories - [Uncategorized](https://davidvonthenen.com/category/uncategorized/) - [Conferences](https://davidvonthenen.com/category/conferences/) - [Kubernetes](https://davidvonthenen.com/category/kubernetes/) - [Personal](https://davidvonthenen.com/category/personal/) - [Storage](https://davidvonthenen.com/category/storage/) - [AI/ML](https://davidvonthenen.com/category/artificial-intelligence-machine-learning/) - [Conversation AI](https://davidvonthenen.com/category/artificial-intelligence-machine-learning/conversation-ai/) - [Voice AI](https://davidvonthenen.com/category/artificial-intelligence-machine-learning/voice-ai/) ## Tags - [Apache Mesos](https://davidvonthenen.com/tag/apache-mesos/) - [Code](https://davidvonthenen.com/tag/code/) - [Conferences](https://davidvonthenen.com/tag/conferences/) - [ContainerCon](https://davidvonthenen.com/tag/containercon/) - [Deep Dive](https://davidvonthenen.com/tag/deep-dive/) - [Docker](https://davidvonthenen.com/tag/docker/) - [EMC World](https://davidvonthenen.com/tag/emc-world/) - [EMC {code}](https://davidvonthenen.com/tag/emccode/) - [External Storage](https://davidvonthenen.com/tag/external-storage/) - [Framework](https://davidvonthenen.com/tag/framework/) - [Fun](https://davidvonthenen.com/tag/fun/) - [Golang](https://davidvonthenen.com/tag/golang/) - [Kubernetes](https://davidvonthenen.com/tag/kubernetes/) - [LinuxCon](https://davidvonthenen.com/tag/linuxcon/) - [Mesos](https://davidvonthenen.com/tag/mesos/) - [mesos-module-dvdi](https://davidvonthenen.com/tag/mesos-module-dvdi/) - [Mesosphere](https://davidvonthenen.com/tag/mesosphere/) - [Personal](https://davidvonthenen.com/tag/personal/) - [SCaLE](https://davidvonthenen.com/tag/scale/) - [ScaleIO](https://davidvonthenen.com/tag/scaleio/) - [ScaleIO Framework](https://davidvonthenen.com/tag/scaleio-framework/) - [Storage](https://davidvonthenen.com/tag/storage/) - [Volume Driver](https://davidvonthenen.com/tag/volume-driver/) - [Artificial Intelligence](https://davidvonthenen.com/tag/artificial-intelligence/) - [Conversation AI](https://davidvonthenen.com/tag/conversation-ai/) - [Machine Learning](https://davidvonthenen.com/tag/machine-learning/) - [EMC](https://davidvonthenen.com/tag/emc/) - [C++](https://davidvonthenen.com/tag/c/) - [Databases](https://davidvonthenen.com/tag/databases/) - [DVDI](https://davidvonthenen.com/tag/dvdi/) - [Elastic Search](https://davidvonthenen.com/tag/elastic-search/) - [GitHub](https://davidvonthenen.com/tag/github/) - [NoSQL](https://davidvonthenen.com/tag/nosql/) - [Travel](https://davidvonthenen.com/tag/travel/) - [IoT](https://davidvonthenen.com/tag/iot/) - [Ubuntu](https://davidvonthenen.com/tag/ubuntu/) - [Dell EMC World](https://davidvonthenen.com/tag/dell-emc-world/) - [how-to](https://davidvonthenen.com/tag/how-to/) - [Medicial](https://davidvonthenen.com/tag/medicial/) - [AI](https://davidvonthenen.com/tag/ai/) - [ML](https://davidvonthenen.com/tag/ml/) - [PyTorch](https://davidvonthenen.com/tag/pytorch/) - [Real Time Communications Conference & Expo](https://davidvonthenen.com/tag/real-time-communications-conference-expo/) - [RTC Conference & Expo](https://davidvonthenen.com/tag/rtc-conference-expo/) - [Voice AI](https://davidvonthenen.com/tag/voice-ai/)