Writing
Notes from production
Applied AI in production environments, backend architecture, and notes from doctoral research. Written to be useful, not to rank.
-
The real trade-off between an API model and a local one
An API model costs nothing until the bill arrives, and a local model costs everything up front, before it answers a single question that matters.
-
What EWC buys you that flat L2 does not
A registered kill-gate compares EWC against a flat L2 control on Permuted MNIST, and the same headline retention number hides two very different costs.
-
Fluency is not understanding
A model that sounds confident is not the same as a model that is right, and nothing in its fluent tone tells you which one you are actually getting from it.
-
How wrong is a model's confidence?
A ResNet-34 on CIFAR-100 claimed 99% confidence while landing correctly 94% of the time; temperature scaling cut the gap by nearly two-thirds.
-
Catastrophic forgetting, measured
A small network lost 12.3 points of accuracy learning a second task, real but short of my registered threshold for severe. EWC recovered 98% of it.
-
Blackwell quantisation on my own card
Q4_K_M more than doubled throughput and cut VRAM by two thirds on my RTX 5070 Ti, staying 98% similar to full precision. The interesting part was where that 2% lived.
-
What the EU AI Act actually requires of a masking layer
The Act never says masking. Three articles, on data, logging and human oversight, each describe a property a masking layer either has or does not.
-
Your model is not the product. The pipeline around it is.
Swap the model and almost nothing changes. Swap the masking layer, the permissions, or the monitoring, and the system stops running or starts leaking.
-
Detecting PII before the model sees it
Two registered experiments, one frozen dataset, two detectors that each miss a different category. The entity-level numbers say which, and by how much.
-
Why I pre-register a kill-gate for every experiment
A kill-gate is the number, written down in advance, at which I abandon my own hypothesis. How three real gates fired, passed and refused to answer.