Conrado Silva Miranda

Conrado Silva Miranda  •  Feb 5, 2024

Rigorous LLM Evaluation With a Human Touch

As the ecosystem around evaluation for large language models (LLMs) matures, it’s important that we continue to keep humans in the loop. In this post, I’ll share how it’s possible to incorporate a human touch while still being rigorous. We’ll start with why this is important in the first place and then cover actionable strategies for building an LLM evaluation system.

Conrado Silva Miranda  •  Aug 16, 2023

Don't Overlook the Operational Challenges of Generative AI

AI challenges: learn why executives weighing generative AI initiatives need to be aware of the operational obstacles that make Gen AI difficult to deploy

Conrado Silva Miranda  •  Jun 14, 2023

AWS US-East-1 Goes Down Again, and People Scream “Multi-Region!” - A Rant

AWS US-East-1 had issues Tuesday, bringing down a lot of the internet. The usual response: People scream, 'Multi-regions!' But that's hard to implement.

Conrado Silva Miranda  •  Dec 1, 2021

3 Reasons Why ML Code Is Not Like Software

In ML code, a copy/paste approach of familiar DevOps processes to the unfamiliar task rarely works. There are three main reasons why; learn them here.

Conrado Silva Miranda  •  Nov 13, 2020

How to Deploy ML models with AWS Lambda

AWS Lambda deployment for ML: This post talks about how to get started with deploying models on AWS Lambda & pros and cons of using this system for inference.

Conrado Silva Miranda  •  Aug 25, 2020

The Third Wave of Operationalization is Here: MLOps

Operationalization in AI is the key to success while most companies fail at extracting value from using machine learning models in products prorerly.