MG Signal · Gen AI · Agentic AI
The Bottleneck Was Never the Code
A one-page spec produced working software in an hour. Everything between that and a product people could depend on was not in the page, because nobody had decided it yet.
Read →Writing
From the field.
Real lessons from building and deploying AI.
MG Signal · Gen AI · Machine Learning
Old Mathematics Quietly Powers Modern AI
Eigenvalues shaped search in 1990 and ranked the web in 1998. They still sit under embeddings, PCA and LoRA. The small end of the spectrum may have one more use.
Read →MG Signal · Machine Learning · Survival Analysis
Everyone Predicts Failure. Few Predict Time.
Failures were rare, so most of our data wasn't failure data. Survival analysis let every observation contribute what it actually knew, instead of forcing a label.
Read →MG Signal · Machine Learning · Anomaly Detection
Why We Stopped Using Western Electric Rules
The zone rules assume a distribution most real processes don't have. We kept Rule 1, made the limits adaptive, and handled drift as a separate problem.
Read →MG Signal · Gen AI · Machine Learning
Analytics Didn't Go Away. It Got More to Work With.
Traditional Analytics and ML aren't obsolete. GenAI turns years of unreadable text into data they can use, then explains the results back to people.
Read →MG Signal · Gen AI · Agentic AI
The Model Is Only 10% of Your AI Agent
In any agentic system, the model is about 10%. The other 90% is data engineering. An anatomy of one agent turn—and why the leverage was never in the model.
Read →Machine Learning · AI
Data Science, ML, AI: The Map Most People Get Backwards
Most people think AI means ChatGPT. Here's how Data Science, Machine Learning, and AI actually relate — an intersection, not a hierarchy — and what it all rests on.
Read →