The Machine Learning Pivot

The Machine Learning Pivot

Home
📚 Tutorials
About

November 2025

How to Save $150K/Year Self-Hosting LLMs
Self-hosting LLMs saves $150,000 per year at scale. But going production-ready the wrong way burns that savings fast. Learn the deployment strategies…
 • The Machine Learning Pivot
Self-Hosting LLMs with vLLM
Get ready to save some money 💰. In this post, you'll learn how to set up your own LLM server using vLLM, choose the right models, and build an…
 • The Machine Learning Pivot
Testing Your LLM Applications (Without Going Broke)
Traditional software is deterministic. Same input, same output, every time. LLMs? Non-deterministic by design. Same input, different output. Even with…
 • The Machine Learning Pivot
Stop Guessing What Your LLM Returns
If you don't know what datatypes your LLM function returns, you're basically playing Russian roulette during runtime 😨
 • The Machine Learning Pivot
The Six Problems Hiding in Your LLM Notebook Code
Right now, there's probably a data scientist waking up to a $3,000 OpenAI bill because a bot found their exposed API key and has been hammering GPT-4…
 • The Machine Learning Pivot
Random Sampling Is Sabotaging Your Models!
Did you know diversity can detect hallucinations? Ask an LLM "what's the capital of France" five times and you'll get some variation of "Paris" over and…
 • The Machine Learning Pivot
© 2026 The Machine Learning Pivot · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture