Tag: Machine Learning
-
Stop Using Temperature 0 for LLM Evals: Why It Breaks Benchmarks
Temperature 0 breaks LLM evals by hiding variance and selecting for memorization. Here's why you should sample at 0.5 instead โ with real accuracy gaps.
-
AutoML Is Overrated: Why Manual Tuning Wins for Beginners
AutoML promises fast results but hides the lessons beginners need most. Manual tuning teaches bias-variance tradeoffs AutoML skips โ here's why.
-
MLflow Quickstart 2026: Track Your First Experiment in 10 Minutes
Track ML experiments with MLflow in under 10 minutes โ log params, metrics, and models in 3 lines of Python. Real benchmarks on sklearn and PyTorch.
-
My ML Crypto Trading Bot Lost Money: 2 Hard Lessons
I built an ML crypto trading bot, ran it live for weeks, and lost money. The two lessons that mattered most weren't about machine learning at all.
-
DVC Basics: Track Your First ML Dataset in 3 Commands
Track your ML dataset with 3 DVC commands: init, add, push. Real workflow examples, storage math, and the cache gotcha that surprises everyone.
-
Factor Models vs ML: Alpha with 200 Samples, Not 200K
Compare factor models and ML for alpha generation in low-data regimes. Learn why traditional quant methods outperform deep learning with limited samples.
-
Rule-Based to ML PHM Migration: 4-Week Python Roadmap
Cut false alarms by 60% and get 2-week failure warnings. Step-by-step migration from threshold rules to ML models with real Python code.
-
MLflow Experiment Tracking: Portfolio Project in 30 Min
Build a real MLflow experiment tracking portfolio in 30 min: 40+ logged runs, CV metrics, model registry, and a live UI โ not a toy notebook screenshot.