Open source is becoming one of the most important forces in AI.

In this episode of The Private AI Lab, Johan speaks with Rhys Oxenham and Sanjeet Singh from SUSE about the role of open source in building enterprise AI platforms.

They explore:

• The difference between open source AI infrastructure and open-weight models

• Why enterprises are moving toward private AI deployments

• The growing importance of digital sovereignty

• Innovation happening in the open source AI ecosystem

• Why specialized models may challenge large frontier models

• How SUSE helps organizations deploy AI platforms securely

The episode also previews NVIDIA GTC, where open source AI is a major theme.

All Open Source AI sessions in the content catalog:

https://www.nvidia.com/gtc/session-catalog/?search=open%20source

Register for NVIDIA GTC today using the following link:

https://nvda.ws/4qXGFjm

What should you expect from NVIDIA GTC 2026?

In this pre-show episode of The Private AI Lab, Johan talks with Dirk Glücker, AI platform engineer and Kubernetes specialist, about the sessions, technologies, and trends worth watching at this year’s conference.

They discuss:

• The unique culture of GTC compared to other tech conferences

• Key sessions around MLOps, distributed inference, and AI infrastructure

• What we might see in Jensen Huang’s keynote

• The evolution of AI factories and large GPU clusters

• Why networking and meet-the-expert sessions are invaluable

• Practical advice for navigating GTC (or watching remotely)

If you’re building AI platforms, running GPU infrastructure, or following the latest developments in accelerated computing, this episode is a great primer before the event.

Links mentioned:

AI Fail video from Dirk:

https://www.youtube.com/watch?v=CWGefSIVIKM

All hybrid sessions in the content catalog:

https://register.nvidia.com/flow/nvidia/gtc26/ap/page/catalog?tab.catalogallsessionstab=16566177511100015Kus&search.viewingexperience=1700085746191002Cnn0

Register for NVIDIA GTC today using the following link:

https://nvda.ws/4qXGFjm

Chapters:

00:00 – Welcome to the GTC pre-show

00:40 – Meet Dirk Glücker

01:20 – AI fail of the week: robot meets mirror

04:10 – Physical AI and robotics challenges

05:20 – What GTC is like for first-time attendees

07:50 – Highlights from last year’s conference

08:10 – DGX Spark and AI factories

09:10 – Why meeting experts at GTC matters

12:20 – How to plan your GTC schedule

13:00 – MLOps sessions worth attending

14:30 – AI coding agents and development automation

16:10 – Distributed inference at scale

17:00 – Inside NVIDIA’s inference ecosystem

18:00 – AI infrastructure and platform engineering

19:30 – Multi-tenant GPU clusters

21:00 – Pixar rendering pipelines and GPUs

22:00 – Formula One and AI performance

23:00 – Watching GTC remotely

24:00 – Open source inference and sovereign AI

26:30 – Overlapping sessions and planning strategy

27:10 – Predictions for Jensen Huang’s keynote

31:00 – AI factory networking infrastructure

33:00 – Exploring the GTC expo floor

37:00 – Tips for first-time attendees

44:00 – Final thoughts before GTC

Is vibe coding the ultimate productivity accelerator — or a fast track to 4AM production outages?

In this episode of The Private AI Lab, Johan speaks with Andrew Morgan about the real state of vibe coding in 2026.

They unpack the difference between vibe coding and vibe learning, explore the risks of blindly trusting AI-generated code, and debate whether this new wave of AI-native development is democratizing software engineering — or quietly lowering the bar.

The conversation covers rogue agents, context window limits, guardrails, on-prem AI strategies, enterprise accountability, and why thinking might become the most important engineering skill of the next decade.

This episode is for developers, platform engineers, architects, and anyone navigating AI-assisted software development.

00:00 – Welcome to The Private AI Lab

01:40 – Andrew’s biggest AI fail

03:00 – The sunken cost fallacy of prompting

04:45 – Rogue agents & expensive mistakes

06:30 – Skynet jokes (but not really)

07:20 – What is vibe coding?

09:00 – Trust, guardrails & blast radius

10:15 – The current tooling landscape

12:00 – Vibe coding inside teams

14:40 – Stack Overflow vs vibe coding

17:00 – Code completion on steroids

18:30 – Who’s using it most aggressively?

20:45 – Democratization or dilution?

23:00 – Accountability at 4AM

25:00 – Lazy engineers vs lazy vibecoders

27:00 – Debugging AI-generated code

30:00 – Crab dragons & technical debt

32:30 – DevOps knowledge & production readiness

35:00 – Human vs AI code reviews

37:30 – Private AI & vibe coding

40:00 – On-prem vs cloud agents

42:30 – Context windows & hallucinations

44:00 – The next 18 months

47:30 – Strong engineers vs weak engineers

49:30 – Security risks & red teaming

52:00 – Is thinking the new bottleneck?

54:00 – Final lab report & takeaways

What if deploying private, enterprise-grade AI didn’t take months—but only as long as it takes your coffee to cool?

In this episode of The Private AI Lab, Johan van Amersfoort sits down with Tasha Drew to unpack how Private AI Services on VMware Cloud Foundation are changing the way enterprises build and consume AI.

They discuss why AI needs a platform layer, how Broadcom integrates open source responsibly, what MCP means for enterprise AI, and how agentic AI workloads can be deployed securely, governed properly, and operated at scale—inside the private cloud.

If you like to follow Tasha, you can do that on linkedin:https://www.linkedin.com/in/tashy/

Topics covered

• Why “training” is the most misused AI term

• From zero to RAG and agentic AI in minutes

• Private AI Services and the VCF strategy

• Model runtime, API gateways, and GPU efficiency

• Data indexing & retrieval for enterprise RAG

• Open source trade-offs: speed vs flexibility

• MCP, tool usage, and governance

• How Broadcom uses its own AI platform internally

• The future of agents: specialists over monoliths

If you like to follow Tasha, you can do that on linkedin:https://www.linkedin.com/in/tashy/

In this episode of The Private AI Lab, Johan van Amersfoort speaks with Adam Grzywaczewski, a senior Deep Learning Data Scientist at NVIDIA, about the rapidly evolving world of AI inference.

They explore how inference has shifted from simple, single-GPU execution to highly distributed, latency-sensitive systems powering today’s large language models. Adam explains the real bottlenecks teams face, why software optimization and hardware innovation must move together, and how NVIDIA’s inference stack—from TensorRT-LLM to Dynamo—enables scalable, cost-efficient deployments.

The conversation also covers quantization, pruning, mixture-of-experts models, AI factories, and why inference optimization is becoming one of the most critical skills in modern AI engineering.

Topics covered

• Why inference is now harder than training

• Autoregressive models and KV-cache challenges

• Mixture-of-experts architectures

• NVIDIA Dynamo and TensorRT-LLM

• Hardware vs software optimization

• Quantization, pruning, and distillation

• Latency vs throughput trade-offs

• The rise of AI factories and DGX systems

• What’s next for AI inference

In this episode of The Private AI Lab, Johan van Amersfoort talks with Maxime Colomès about the Model Context Protocol (MCP)—one of the most important emerging standards in AI today.

MCP is often described as the USB-C of AI: a universal way for AI models to connect to tools, data sources, and real-world systems. Maxime explains what MCP is, how it works, and why its recent donation to the Linux Foundation is such a major milestone for the AI ecosystem.

They explore real-world enterprise use cases, MCP security considerations, private AI architectures, and how MCP integrates with platforms like OpenShift AI. The conversation also touches on developer productivity, AI agents that can take action, and the future of personal, privacy-preserving AI assistants.

Key topics

• What the Model Context Protocol (MCP) is and why it matters

• MCP vs traditional APIs and plugin systems

• Enterprise MCP architectures and gateways

• MCP and private AI / data sovereignty

• OpenShift AI and MLOps workflows

• Security risks and best practices with MCP

• Community MCP servers and registries

• Future MCP use cases and predictions

In this episode of The Private AI Lab, Johan sits down with Frank Denneman to explore the past, present, and future of VMware’s Private AI portfolio.

This conversation goes beyond AI buzzwords and marketing fluff. Together, Johan and Frank dive deep into the real infrastructure and resource management challenges that emerge when AI workloads enter enterprise environments. GPUs, scheduling, isolation, and platform design all take center stage—viewed through the lens of real-world VMware deployments.

If you are an infrastructure architect, platform engineer, or IT decision-maker designing AI behind the firewall, this episode provides grounded insights into what actually matters.

🔍 What you’ll learn in this episode

• How VMware’s Private AI strategy has evolved over time

• Why AI workloads fundamentally change infrastructure assumptions

• The importance of resource management for GPU-backed workloads

• Key architectural trade-offs when running AI on-prem

• How to think about the future of enterprise AI platforms

🎧 Listen & Subscribe

For more experiments, insights, and behind-the-firewall AI discussions, visit johan.ml.

Experiment complete. Until the next one — stay curious.

This episode of The Private AI Lab features Robbie Jerrom, Principal Technologist AI at Red Hat, for a deep dive into Private AI, from the DGX Spark to OpenShift AI and the future of agentic systems.

Topics we cover:

• How Robbie uses the DGX Spark for home-lab AI

• Why developers are moving from cloud GPUs to local devices

• OpenShift AI as a consistent platform from experiment to production

• The best open-source components for modern AI stacks

• Why 79% of POCs never reach production — and how to avoid that

• The next wave: agentic AI and enterprise automation

Watch on YouTube:

https://www.youtube.com/watch?v=jjyB8w_cpb0

More episodes & articles at johan.ml

In this episode of The Private AI Lab, Johan is joined by Andrew Foe, CEO of Iodis and HyperAI, to explore the NVIDIA DGX Spark from a real-world perspective.

We cover:

• Unboxing & first impressions

• Bring-up and setup tips

• Everyday usability

• What customers love

• The most common misconceptions

• Why preorder demand exploded in the BeNeLux region

A must-listen for anyone exploring Private AI hardware or considering the DGX Spark.

🎧 Watch on YouTube: https://www.youtube.com/watch?v=jENCTgcAWsI

💡 More experiments: https://johan.ml

In the premiere of The Private AI Lab, Johan van Amersfoort is joined by SUSE AI Specialist Eric Lajoie to talk about sovereign AI, deploying chatbots in under an hour, and the unexpected hazards of robotic dogs.Timestamps:

00:00 – Intro & guest welcome

01:04 – How to pronounce “Lajoie”?

02:00 – What Eric actually does at SUSE

05:14 – Eric’s AI fail: a very personal RAG demo

10:06 – What Private AI means to Eric

11:30 – How SUSE AI works (chatbots, Kubernetes, Rancher, and more)

21:30 – RAG architecture explained

26:00 – 40-minute SUSE AI deployment?!

31:00 – Real-world use cases (GPUaaS, observability, MCP)

39:00 – AI sovereignty in Europe

43:00 – Wrap-up & key takeaways

54:00 – Eric’s prediction for the next 12 months in AI

57:40 – Johan’s robot dog fail

60:00 – Outro + where to follow Eric

🔗 Links & Mentions • Learn more about SUSE AI: https://suse.com

Follow Eric: https://www.linkedin.com/in/elajoie/ or lajoie.de

Check out the companion post at https://johan.ml/

Related episode: When Shit Hits The Fan ft. Eric – https://open.spotify.com/episode/2IeLq8WT7eqMJPVkcUMg3G?si=eaf7a529a75e4078