PortfolioPublic archive Private studio

Evidence before
confidence.

Notes on Physical AI, autonomous-driving systems, and the engineering choices between a model and a moving vehicle.

7 published notes
01

Engineering Case Study

Architecture, interfaces, validation, and the operational failure envelope.

CyberRT · BEV/OCC · Operations

Baidu Apollo 11.0: Open Source Is Valuable When It Closes an Operational Loop

Apollo 11.0 is moving from a collection of driving modules toward an operational system for delivery, sweeping, patrol, and shuttle vehicles. That shift changes what open-source maturity means.

Baidu Apollo 11.0: 오픈소스의 가치는 운영 루프를 닫을 때 생긴다
Feb 10, 20269 min · EN / KO
Sensor suite · Validation · Scale

Waymo’s Sixth-Generation Driver: Scaling Is a Hardware–Validation Co-Design Problem

Waymo’s 2026 move to fully autonomous operation with its sixth-generation Driver shows that reducing sensors is only defensible when fleet learning and validation preserve redundancy.

Waymo 6세대 Driver: 확장은 하드웨어와 검증의 공동 설계 문제다
Feb 23, 20268 min · EN / KO
02

Technical Insight Memo

A compact position on a technical or industrial shift.

Training · Simulation · Inference

NVIDIA at CES 2025: The Autonomous Vehicle Is Becoming a Three-Computer System

NVIDIA’s CES message was not a single chip announcement. It was a systems argument: training, simulation, and in-vehicle inference must be designed as one closed engineering loop.

NVIDIA CES 2025: 자율주행차는 세 개의 컴퓨터로 재구성되고 있다
Jan 15, 20256 min · EN / KO
Edge NPU · 4D radar · Fusion

DEEPX and DeepFusion AI: Korea’s Physical-AI Opportunity Is Between the Sensor and the Cloud

CES 2026 showed two complementary infrastructure bets: ultra-low-power edge inference and learned 4D-radar sensor fusion. Their real value appears when they are evaluated as one latency-and-power budget.

DEEPX와 DeepFusion AI: 한국 Physical AI의 기회는 센서와 클라우드 사이에 있다
Jan 20, 20267 min · EN / KO
03

Deep Dive / Paper Reproduction

Models, silicon, and algorithms examined below the headline.

VLA · Long tail · Distillation

Alpamayo: Why an Autonomous Vehicle Needs a Reasoning Teacher, Not a Chatbot Driver

NVIDIA’s reasoning VLA is most useful as a teacher model for long-tail decisions. The engineering question is how to distill its explanations into a bounded, testable driving policy.

Alpamayo: 자율주행차에 필요한 것은 챗봇 운전자가 아니라 추론 교사다
Jan 18, 20269 min · EN / KO
SoC · Compiler · Vehicle OS

China’s Custom AV Silicon Is About Controlling the Iteration Loop, Not Winning a TOPS Contest

NIO’s NX9031, XPENG’s Turing chips, and Li Auto’s MAHE M100 reveal a broader strategy: align the model, compiler, vehicle OS, sensors, and product cadence under one architecture.

중국 자율주행 커스텀 실리콘의 목적은 TOPS 경쟁이 아니라 반복 루프의 통제다
Jun 9, 20269 min · EN / KO
04

Build Log

A shorter field note on a system, prototype, or engineering question.

Privacy · CXL · Edge systems

GhostPass and Panmnesia: Two CES 2025 Lessons in Moving Trust to the Edge

One startup keeps biometric identity on the user’s phone; the other brings terabytes of memory closer to the GPU. Both redesign the boundary where sensitive or expensive state should live.

GhostPass와 Panmnesia: 신뢰를 엣지로 옮기는 CES 2025의 두 가지 방식
Jan 22, 20257 min · EN / KO