A store selling pet supplies and gaming gear had a search bar that put cat nip next to Logitech mice. Notes on how self-attention and the Query-Key-Value setup finally gave that search enough context to tell an animal from a USB device.
I built a client the dashboard they asked for: 24 SQL queries, three tabs, four seconds slower. They stopped opening it after a week. What worked was cutting every metric that would not change a decision, and burying the data dump in an export tab.
A health-tech client had 99.8% accuracy on a disease that shows up in 0.2% of patients. Their agent said no to everyone. Here is how I pulled a continuous risk score out of a binary agent so the AUC comparison against their XGBoost model meant something.
A weather dashboard that tells people what to wear, built on Databricks and GPT-4o-mini instead of a pile of if-statements. Covers the extraction class, the LLM transformation step, and the hourly job that keeps the Delta Table fresh.
An AI engineer wires up models that already exist. A machine learning engineer builds the model. Which one you hire decides whether you ship in two weeks or spend six months in a sandbox, and here is how I tell the two jobs apart.
The RTX 30-series has no hardware FP8, so I packed four FP8 values into one FP32 container and unpacked them inside a Triton kernel. On a client’s 3080s that cut the memory bottleneck and ran about 3.3x faster.
A price tracker taught me that a hand-built Google scraper dies within two days. Here is why I hand that job to SerpApi now, plus the PHP wrapper I reuse and the latency setting that matters at scale.
A hanging WooCommerce checkout on Black Friday taught me that a nicer spinner does not calm anyone down. Notes on cognitive tunneling, single-tasking flows, transient locks against panic clicks, and what an emergency mode looks like.
A client thought their WooCommerce recommendation engine was broken because accuracy at a 0.5 threshold read 51%. The ranking was fine, the threshold was not. This walks through checking AUC in a spreadsheet with sorted scores and the trapezoidal rule.
A WooCommerce recommendation engine kept timing out the server, and the weights oscillated instead of settling. Swapping the basic update rule for Momentum and then Adam is what fixed it, and this explains why adaptive step sizes matter on messy data.