Exploring what's new, and what actually matters.

A repeatable agent workflow kept skipping different steps on different runs. The fix wasn't a stronger prompt; it was moving the plan into a DAG and letting deterministic code control sequence and verification.

People keep asking me a version of the same question: what NVIDIA hardware should I be thinking about for a digital twin, from a developer build at my desk all the way to production? I always had an answer but no clean model behind it, just a pile of product names, three of which are confusingly all called DGX. So I built the model I wanted: NVIDIA develops one architecture family a year and expresses it across many kinds of computer, from a gaming card to a liquid-cooled rack. These are my rough notes, in case you're coming at it from the software side and asking the same thing.

Running the training loop for real surfaced one concept the diagram doesn't capture: the same five stages take two different shapes depending on how the robot learns — by trial and error (reinforcement learning) or by copying demonstrations (imitation). This part is the mechanism behind that fork, grounded in the two tasks I ran, plus the open questions the build left unproven. Part 2 of two.

A month ago I drew a five-stage loop for a robot training center and admitted most of it was an educated guess I hadn't tested. So I built the loop as a real, orchestrated pipeline on one GPU and carried two tasks around it — a pole that balances by trial and error, and a Franka arm that learns to stack cubes by copying demonstrations. This is the environment, the stack, the architecture, and what actually ran. Part 1 of two.

When a general-purpose LLM (or an agent built on it) doesn't fit the problem, the reflex is to fine-tune it. I think that's usually the third thing to try, not the first. There are three ways to close the gap: grounding context, harness optimization, and fine-tuning, and which one you reach for should depend on the need in front of you: domain knowledge, agent behavior, or raw performance.

MES was never really about running the machines. It was about improving the operation, and it was throttled by two assumptions baked into how it was built. Physical AI and agentic AI, on one shared model, overturn both. Here's why I think that's a genuine step change, not a smarter widget.

The serious names and serious money are pivoting from language models to world models. I think it's the right shift for physical AI, and one to watch early.

A browser-based USD viewer, RTX-rendered server-side and streamed over WebRTC, built to see if the library-first pitch holds up under real interactivity.

We finally have models that can watch the physical world, reason about it, and predict what happens next. Walk a real automotive parts-kitting task through what they actually solve, and the thing still standing between a demo and a working line isn't a smarter model: it's the policy you have to train for your machine, and the system that keeps it trained.

Kit and libraries used to be the same choice for building on Omniverse. They're not anymore, and that's a bigger change than it looks, with a real before/after from a Kit extension I built.

Since May 2026, Omniverse is free for production, not just development. It's a clean, sensible change, but it landed quietly, and I keep meeting customers and partners who don't know it happened yet. Here's what changed and what it means.

Someone asked me how you'd build a training center for industrial robots from scratch, and my first reaction was that it isn't one project, it's ten. What untangled it was seeing that they aren't ten separate things at all. They're five stages of one loop that turns real work into robot skills and feeds what happens back in. This is where I've gotten so far, still learning, sharing it in case you're walking the same road.

The "Omniverse is just a rendering tool" take isn't a documentation problem. Better explaining won't fix it. Here's why I think that, and what would actually move the perception instead.

Omniverse gets treated as a rendering tool, the thing that makes the demo videos look good. It's actually a stack, and the renderer is one layer out of six. Here's what's underneath the image.