LLM Demo to Production: The Layers That Make an LLM Application Reliable
Taking an LLM from demo to production takes more than a better model. Continue reading on Medium »
Machine Learning stories and sources
Scan recent stories matching this search, find the sources covering it most often, and open complete briefs for the stories that matter.
Stories12Sources5
Where this search is showing up.
Recent context to explore
7 ML Infrastructure Tricks That Turned My Slow Experiments Into Production Systems Overnight
These aren’t nice-to-haves ,they’re the difference between a prototype and something that actually scales. Continue reading on Medium »
Engineering principles in ML
Representation, Evaluation, and Optimization are the main 3 building blocks when it comes to making a great machine learning model. Continue reading on Medium »
Choosing Between DeepSeek, Qwen, Kimi, and GLM at Scale
Choosing Between DeepSeek, Qwen, Kimi, and GLM at Scale Six months ago, my cloud bill was scaring me. We were running everything through a single Western LLM provider, and the cost of inference was eating our runway alive. That's when I started digging seriously into the Chinese model ecosystem — not as a political sta
Monitoring discriminative ML models using Amazon SageMaker AI with MLflow
Implementing a data and model monitoring solution is necessary to maintain prediction accuracy and help achieve the best outcome for your machine learning use case. This post shows how you can use open source Evidently together with Amazon SageMaker AI to generate monitoring reports, organize and compare the results in
Your ML Model is Live — But is it actually being tested?
I came across a Google research paper recently — “The ML Test Score” — and it honestly changed how I think about testing AI systems. The… Continue reading on Medium »
Model Evaluation
In Supervised learning, we often indirectly optimize the outcome by seeing how well the machine learning model scores on the training data… Continue reading on Medium »
Deploying quantized models on Amazon SageMaker AI with Unsloth
In this post, you will learn four deployment patterns for taking models that have already been quantized with Unsloth and deploying them on AWS infrastructure. The patterns use Amazon Elastic Compute Cloud (Amazon EC2) for direct instance access, Amazon SageMaker AI inference endpoints for managed serving, and Amazon E
Deploying Agents: Containers, Orchestration, and Scaling the Loop
Book: Agents in Production — Building, Tracing, and Shipping Multi-Step AI You Can Trust Also by me: Observability for LLM Applications — the companion book in The AI Engineer's Library (2-book series) My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools Me: xgabri
The Fundamentals of AI: Making AI practical
Training a large language model (LLM) can cost millions of dollars, and deploying one at scale can cost millions more. Despite this, the raw model straight out of training is often the wrong tool for any specific job. This is the gap that AI.......
LLM Evaluation Frameworks Compared: How to Actually Measure What Your Model Does
In this article, you will learn how to evaluate LLM applications using the three dominant open-source frameworks — RAGAS, DeepEval, and Promptfoo — and why...
Use this search in the app
Open the app to save searches, scan fresh stories, and keep useful reads in one flow.