Mobile Robotics
The dual-brain robot got the split right and the address wrong — and defense already showed us the fix. In the span of a few weeks, three robots told the same story without realizing it. In Shanghai, Jaka unveiled Pi — a compact 1.22-meter humanoid with what the company
The Un-Engineering Lens
Why thin robots, sovereign fleet inference, and private 5G-Advanced — not bigger on-board VLA models — will define the next phase of Physical AI. A first-principles look at the most expensive architectural assumption in humanoid robotics — and why the DRAM super-cycle just made it untenable. I spent the
The Un-Engineering Lens
20 years of living with ADAS, and the feedback loop that was never built A first-principles engineering critique of the architecture behind every false bing, phantom brake, and nuisance lane-keeping intervention you have ever experienced — and the single OEM that built it differently. Last month I quietly passed
The Un-Engineering Lens
An April 2026 Lens on what the AI press got wrong — and what actually shifted. The press told you AI exploded this month. Mythos benchmarks. Boston Dynamics victory laps. Robot wolfpacks on Chinese state TV. Five new agentic models in three weeks. Bezos wiring $100 billion into industrial AI. Musk
The Un-Engineering Lens
What Auto China 2026, DeepSeek V4 and Tesla’s Q1 just quietly agreed on — and why the TOPS race is over. April 22–26, 2026 looked like three unrelated events. Tesla reported Q1 earnings on Tuesday. DeepSeek dropped V4 on Hugging Face on Friday. Auto China 2026 opened in Beijing
has-substack
How UWB became the safety and memory layer the humanoid stack was quietly missing. AgiBot just declared 2026 "Deployment Year One" at its Shanghai partner conference, rolled out five new robot platforms, eight foundation models, and the 10,000th unit off the line. The YouTube transcript circulating the
The Un-Engineering Lens
Why Hyundai Won the Humanoid Race Before Anyone Noticed THE LENS IN ONE PARAGRAPH Atlas is not one robot. It is three stacks in a trench coat — cognition, embodied control, and actuation — each owned by a different company with a different economic curve. Google failed because it wanted the whole
The Un-Engineering Lens
Most vehicles can’t even run a container. Calling them AI-defined is premature. At Mobile World Congress Barcelona in March 2026, LG Electronics unveiled a next-generation smart telematics solution—a combined TCU-antenna module integrating 5G, GPS, V2X, and satellite communications into a single unit. The engineering is
The Un-Engineering Lens
A Four-Layer Resilience Architecture for Autonomous Fleets On the evening of March 31, 2026, over 100 Baidu Apollo Go robotaxis simultaneously froze on the elevated expressways of Wuhan, a city of 14 million. Vehicles halted in fast lanes with traffic streaming past. In-car SOS buttons failed. One passenger
Mobile Robotics
Physical AI, Thinner Control, Spatial Memory, TurboQuant, Code Modernization, and the Robotaxi Inflection March 2026 did not politely announce itself. It detonated across every layer of the Physical AI stack—from silicon-level compression to embodied spatial cognition to the streets where robotaxis now compete for passengers—and confirmed several
The Un-Engineering Lens
The Great Rewrite: From C/C++ Spaghetti to Memory-Safe Rust Microservices How DARPA TRACTOR, AI Agent Teams, and Regulatory Pressure Are Forcing the Largest Code Migration in History The Ticking Clock on Unsafe Code Seventy percent of all disclosed security vulnerabilities in large systems trace back to a single
The Un-Engineering Lens
On Tuesday, Google Research dropped a quiet bombshell. TurboQuant — a training-free compression algorithm that shrinks the key-value (KV) cache of large AI models by 6x and accelerates inference by up to 8x — sent memory chip stocks tumbling within hours. SK Hynix, Samsung, Micron: all fell sharply. The internet,