iiinova — where your digital self keeps evolving

Santiago Viquez @santiviquez.com · 09/02/2025

It's happening! Join us next week to ask Sebastian Raschka anything! 📅 Date: February 11th ⏰ Time: 10:00 AM – 11:00 AM EST 📍 Register: lu.ma/evqa4rct

011

Santiago Viquez @santiviquez.com · 21/01/2025

Super proud to work at a place that values open science. Four years ago, at NannyML, we invented the first version of Confidence-Based Performance Estimation. Today, a paper about it was published in JAIR. JAIR: jair.org/index.php/ja... ArXiv: arxiv.org/abs/2407.08649

121

Santiago Viquez @santiviquez.com · 18/01/2025

Took me over an hour to fully understand the computation behind the Pair Confusion Matrix. Hopefully, it’ll take you a lot less after reading my explanation in "The Little Book of ML Metrics" www.nannyml.com/metrics?via=...

020

Santiago Viquez @santiviquez.com · 18/01/2025

You can just do many things. Yesterday was my first day at culinary school!

020

Santiago Viquez @santiviquez.com · 16/01/2025

If people don’t think what you do is cringe, then you’re not pushing hard enough. Every person you admire was once considered cringe by someone. A Writer, YouTuber, Founder, Musician, you name it. They all got to where they are because they constantly shared their work with the world. Constantly.

130

Santiago Viquez @santiviquez.com · 13/01/2025

We’re deciding what book to read next in the "AI from Scratch" study group. So far, we have these two: 1. AI Engineering by Chip Huyen 2. Hands-On Generative AI with Transformers and Diffusion Models by Omar Sanseviero and gang Any other suggestions?

130

Santiago Viquez @santiviquez.com · 12/01/2025

First AI from Scratch session of 2025! A big thanks to @carloscapote.bsky.social and Michael Erasmus for their excellent explanations in today's meeting.

041

Santiago Viquez @santiviquez.com · 10/01/2025

Forgot to share the news, but here it is: Our NannyML open-source package reached 2,000 GitHub stars! 🌟 Slowly but steadily 💪

010

Santiago Viquez @santiviquez.com · 09/01/2025

Another one from the book. Log Loss (aka cross-entropy loss)! --- If you're interested in more metric descriptions like this one, check out the book I'm writing: The Little Book of ML Metrics. GitHub Repo: github.com/NannyML/The-... Pre-order the book:https://www.nannyml.com/metrics

010

Santiago Viquez @santiviquez.com · 08/01/2025

Which ranking metrics am I missing? In the coming weeks, I'll be working on the ranking chapter for "The Little Book of ML Metrics", and I want to make sure I'm not missing any popular ranking/recsys metrics.

230

Santiago Viquez @santiviquez.com · 02/01/2025

ML Books I'll Be Reading in 2025 📚 1. "AI Engineering: Building Applications with Foundation Models" (Huyen, 2024): amzn.to/4gtQgJo We’ll probably read it in the study group "AI from Scratch."

182

Santiago Viquez @santiviquez.com · 30/12/2024

During the pandemic—specifically, on May 7, 2020—I wrote some goals on a piece of paper. I folded it, stored it in my wallet, and forgot about it. Today, I found it and realized I’ve accomplished all of them.

110

Santiago Viquez @santiviquez.com · 17/12/2024

Univariate data drift doesn't show the full picture. Take a look at this demo created by my colleague @anopsy.bsky.social There are two univariate distributions (top and right) which remain almost unchanged during the whole process.

141

Santiago Viquez @santiviquez.com · 16/12/2024

Yesterday I forgot to post about our study group meeting 😅 It was an amazing one! @carloscapote.bsky.social walked us through Chapter 5: Pretraining on Unlabeled Data. Next week, we’ll take a short break, but we’ll be back after the holidays to finish Chapters 6 and 7 💪

031

Santiago Viquez @santiviquez.com · 12/12/2024

F1-score often takes all the credit. But what F1-score doesn't want you to know is that it wouldn't be so popular without its big brother, F-beta. Check out other metrics at: github.com/NannyML/The-...

031

Santiago Viquez @santiviquez.com · 10/12/2024

800 GitHub stars on The Little Book of ML Metrics 🌟 But even more exciting than the stars is that for the past week, every day I've been waking up to at least two PRs from the community helping me write the book 🔥

010

Santiago Viquez @santiviquez.com · 08/12/2024

Today’s session was a fun one. We started putting everything together and implemented a GPT model. My favorite part of the book is the way Sebastian outlined and structured it to progressively build on previous sections. That alone makes it worth every penny.

030

Santiago Viquez @santiviquez.com · 05/12/2024

Performance metrics are aggregates. Watch out for underperforming segments 👀

010

Santiago Viquez @santiviquez.com · 04/12/2024

There are scenarios where data drift can improve model performance. This happens when the production data moves to regions where the model is more confident in its predictions.

140

Santiago Viquez @santiviquez.com · 30/11/2024

Today, I opened a ton of good first issues. So, if you'd like to help me write The Little ML Metrics Book, hit me up, and I'll guide you through your first issue. github.com/NannyML/The-...

030

Santiago Viquez @santiviquez.com · 27/11/2024

I asked an AI Engineer what it would cost to create this today. I will never forget his answer… “We can’t, we don’t know how to do it.”

031

Santiago Viquez @santiviquez.com · 26/11/2024

Richard S. Sutton: "I'll write an introduction to RL." Also Richard: Writes a 552-page-long book

040

Santiago Viquez @santiviquez.com · 25/11/2024

Today's session was a great one. I feel like the intuition behind Q, K, and V matrices in self-attention finally clicked for many of us.

130

Santiago Viquez @santiviquez.com · 23/11/2024

The weekends are for building LLMs. Join us at reading “Build a Large Language Model (from scratch)” by @sebastianraschka.com

1214

Santiago Viquez @santiviquez.com · 21/11/2024

Today, I was thinking about one of the first blog posts I ever wrote. It was about how a single Snickers bar helped me get the first 1,000 downloads of an app I had made the day before. Aside from being a funny story, this post from eight years ago also helped me land my first job at a startup.

100

Santiago Viquez @santiviquez.com · 20/11/2024

The model makes predictions The predictions drive business actions The actions create a business impact The impact can be positive or negative We need ground truth to evaluate the impact But ground truth takes forever to arrive The model keeps making bad predictions The business suffers

140

Santiago Viquez @santiviquez.com · 19/11/2024

This blog post is probably the most comprehensive, detailed, and approachable explanation of PPO (Proximal Policy Optimization) out there. Love seeing companies invest time in education: www.adaptive-ml.com/post/from-ze...

040

Santiago Viquez @santiviquez.com · 16/11/2024

Tomorrow Sunday at 2 pm UTC we will have our second session. This time we'll discuss text preprocessing and embeddings in detail.

121

Santiago Viquez @santiviquez.com · 11/11/2024

Today, we kicked off the "AI from Scratch" study group, where we are studying the book "Build A Large Language Model (from Scratch)". More than 80 people joined 🤯 Looking forward to the next meeting!

060

Santiago Viquez @santiviquez.com · 07/11/2024

This Sunday, November 10th, will be the first meeting of AI from Scratch, where we will discuss chapters 1 and 2 of the book "Build a Large Language Mode (from scratch)." I sent this over to the Discord server.

120

Santiago Viquez @santiviquez.com · 04/11/2024

99% of data scientists know SMOTE doesn’t work. The other 50% think they can solve class imbalance problems with it.

010

Santiago Viquez @santiviquez.com · 03/11/2024

The energy I bring to bluesky

020

Santiago Viquez @santiviquez.com · 31/10/2024

If you want to scare people this Halloween, dress up as an ML model in prod... without any monitoring.

000

Santiago Viquez @santiviquez.com · 29/10/2024

Let me introduce myself to all the new people who followed! • I’m writing an open-source book about ML metrics: github.com/NannyML/The-... • I run a study group called AI from Scratch, with over 600 members. • I’m trying to get better at writing. • I work as an ML advocate at NannyML.

041

Santiago Viquez @santiviquez.com · 27/10/2024

Started a study group on Thursday hoping to get al least four people… We are now a +500

020

Santiago Viquez @santiviquez.com · 09/06/2023

Today I read an interesting paper about Covariate Shift Adaptation. It presents a technique that involves re-weighting both train and test instances. Link to paper: arxiv.org/pdf/2305.08637…

010

Santiago Viquez @santiviquez.com · 04/06/2023

I'll be sending the second issue of my "Writing my thesis in public" newsletter tomorrow. 💌 Subscribe here if you don't want to miss it: santiviquez.substack.com

000

Santiago Viquez @santiviquez.com · 31/05/2023

I often wonder if what I'm reading is just the setup of a sci-fi novel. (image from the EU AI act)

000

Santiago Viquez @santiviquez.com · 18/05/2023

Summarizing the EU AI Act 👀

000

Santiago Viquez @santiviquez.com · 17/05/2023

Excited to share a little tool I made with my colleagues at NannyML✨ A bot where you can chat with the 107 pages of the EU AI Act document. The first law on AI by a major regulator anywhere. Planned to go into force on June 15th 👀 🔗Link: www.nannyml.com/ai-act

000

Santiago Viquez @santiviquez.com · 27/04/2023

Working on a new blog post from a coffee shop. The blessings of remote work ✨

000