Topic index / 08 entries
Field notes, architecture decisions, and practical guides filed under this recurring subject.
← All topicsAI ENGINEERING
02 September 2026 · 5 MIN READ
I wanted a detection app my kids could use without a single camera frame leaving the device. The answer: RF-DETR quantized to int8, ONNX Runtime Web on threaded WASM, and a static Amplify site.
AI
23 July 2026 · 5 MIN READ
Moonshot AI shipped a 2.8-trillion-parameter open-weight model with a 1M-token context, native vision, and a new attention stack. What's actually new in the architecture, what the benchmarks say, and why it matters for builders.
AI
05 June 2026 · 7 MIN READ
Amazon built two radically different approaches to predicting the future — a proprietary supply chain optimization pipeline (SCOT) and an open-source time series foundation model (Chronos). This post compares their architectures, trade-offs, and when each philosophy applies.
AI
14 May 2026 · 9 MIN READ
A decision framework for choosing between Amazon's Chronos-2 foundation model and custom XGBoost many-models pipelines for demand forecasting. Based on real patterns from SKU-level supply chain work.
AI
24 February 2026 · 9 MIN READ
What TFLOPS actually measures, why FP16 matters for LLMs, and why the most important GPU bottleneck for inference isn't compute at all.
AI
09 February 2026 · 9 MIN READ
A practical walkthrough of how large language models are aligned with human values — from collecting feedback to PPO optimization and the reward hacking pitfalls.
AI
07 February 2026 · 8 MIN READ
Understand how LLM fine-tuning works, when to use it, and how to choose between full fine-tuning, LoRA, soft prompts, and other PEFT methods.
AI ENGINEERING
14 January 2026 · 5 MIN READ
Building a production forecasting application without the complexity of traditional ML model training and feature engineering.