- The study was killed by a device I buried myself
- The LLM bottleneck is moving from data to energy — just not in proportion
- Drift: Domination Comes From Delegation, Not Awakening
- Measuring per-inference energy on a Jetson without an external meter
- Four pitfalls when benchmarking real-time GPU inference on Jetson
- jetson_clocks was hiding the bug: bwmgr_halt and why EMC locking isn't portable
- Optimizing the whole pipeline, not just the model: real-time YOLOv8 on Jetson
- What jetson_clocks survives: stress-testing a 100 Hz loop on Jetson Orin
- It wasn't just the GPU: decomposing the 100 Hz inference penalty on Jetson Orin
- Back-to-back benchmarks lie: a 100,000-cycle study of periodic 100 Hz inference on Jetson Orin Nano Super