Running low on memory on your NVIDIA Jetson? 👀 @garyexplains demonstrates how Jetson Agent Skills can help diagnose issues, optimize resources and configure LLM runtimes using tools like Codex and Claude Code. Watch the latest Tech Nibble:

Running Impeccable in Codex / ChatGPT? Impeccable *won't* find slop reliably without hooks, so check your settings and make sure they're trusted for each project. We just updated our install steps with better info on this:

Running several businesses is easier than running one, and it comes down to a structure you can copy. Microsoft runs everything from Office to Xbox under one structure with a single CEO and 300,000 employees underneath, so a group of small businesses can't be harder than that. When I only had one business I got sucked into every little drama going on inside it, whereas with several I end up doing only the things I'm meant to be doing. Each business repeats the same three roles - a Head of Growth, a Head of Delight and a General Manager who acts as the Swiss Army knife - and my own job is to be the Key Person of Influence across all of them. I break down the full structure in this video:

Run #LLMs# on @NVIDIARobotics #Jetson# without x86 ONNX export. 🚀 #TensorRT-Model-Connect# on reComputer Classic J5012 (#AGXOrin# 64GB, #JP7#.2). @huggingface checkpoint → trtmc build → .bundle on device trtmc run for text gen Tested: #Qwen3-4B# FP16 (~41GB container peak, 64GB recommended) No ONNX hop. Edge LLM/agent ready. Would you use on-device TRTMC for prototyping, or keep ONNX export for production? 👇 Full guide: Get your own one: #NVIDIA# #Jetson# #TensorRT# #TRTMC# #AGXOrin# #EdgeAI# #LLM# #PhysicalAI# #SeeedStudio#