Post

How to get URL link on X (Twitter) App

On the Twitter thread, click on or icon on the bottom
Click again on or Share Via icon
Click on Copy Link to Tweet
Paste it above and click "Unroll Thread"!
More info at Twitter Help

Santiago

@svpino

Jun 2, 2023 • 10 tweets • 5 min read • Read on X

Scrolly

AI will revolutionize the world in the next 3 to 5 years.

But we need more builders: people willing to work and learn solid AI/ML skills.

Here is how you can start:

Most people think that starting is hard. They are wrong.

These recommendations will get you through the first month.

1. Learn to use notebooks
2. Learn to deal with data
3. Learn data visualization
4. Learn basic algorithms
5. Build your first project

Here are a few resources:

But first, let me thank the sponsor for today's post:

Prompts Daily.

AI will not replace you. A person using AI will.

That's why almost 100k people read this newsletter to keep up with the latest AI insights, news, and tools.

Sign up here for free → neatprompts.com/subscribe

For this guide to be helpful, you need to know Python.

If you are comfortable writing Python, keep going. If you aren't, I'd suggest you start there.

1. Learn to use notebooks

You want to learn about notebooks: Jupyter or Google Colab are your friends.

Notebooks are a fantastic way to code, experiment, and communicate your results.

Here is a 30-minute tutorial on Jupyter Notebooks:

2. Learn to deal with data

Pandas is a one-stop shop for this.

"10 minutes to pandas" is an excellent tutorial to get you started on the basics: pandas.pydata.org/pandas-docs/st….

Also, watch this video: .

3. Learn data visualization

It's critical to learn data visualization and how to showcase the work you are doing.

Kaggle's tutorial is a fantastic start: kaggle.com/learn/data-vis…

Also, watch this 6-minute tutorial on Seaborn: .

4. Learn basic algorithms

A few suggestions: Decision Trees, KNN, Linear Regression, and Neural Networks.

Kick it off with the Machine Learning Recipes from Google: youtube.com/results?search…

Before talking about your first project, it's time to go through an end-to-end tutorial that will put everything together for you.

Look at the "Intro to Machine Learning" tutorial.

It's a quick tutorial that will bring together all of the pieces:
kaggle.com/learn/intro-to…

5. Build your first project

The tutorial from the previous step ends with the Titanic exercise. You can find it on Kaggle: kaggle.com/c/titanic/data.

This is everything you need to get started and finish your first Machine Learning project!

• • •

Missing some Tweet in this thread? You can try to force a refresh

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @svpino

Santiago

@svpino

Aug 4, 2025

AI is changing everything. Full stop.

If you still don't get it, watch this.

Look at the attached video. A company using this tool will execute 100x faster than everyone else. There's simply no match for how fast AI can transform what you do.

I'm working here with @PromptQL. They will help you build a reasoning AI that is specialized to your business.

This makes an ocean of difference:

• Connect to all of your data
• Build a massive knowledge graph
• Incorporate your unique know-how
• Learn over time

The learning part is the thing that blew my mind:

You can teach the system how to interpret your data and how you prefer things to be done.

This knowledge can be reviewed, edited, and deployed so everyone at your company starts using the new version of the model.

Read 4 tweets

Santiago

@svpino

Jul 7, 2025

Here is how you can test your applications using an LLM:

We call this "LLM as a Judge", and it's much easier to implement than most people think.

Here is how to do it:

1/11

(LLM-as-a-judge is one of the topics I teach in my cohort. The next iteration starts in August. You can join at .)

2/11ml.school

We want to use an LLM to test the quality of responses from an application.

There are 3 scenarios:

1. Choose the best of two responses
2. Assess specific qualities of a response
3. Evaluate the response based on additional context

3/11

Read 11 tweets

Santiago

@svpino

Jun 6, 2025

Bye-bye, virtual assistants! Here is the most useful agent of 2025.

An agent with access to your Gmail, Calendar, and Drive, and the ability to do things for you is pretty mind-blowing.

I asked it to read my emails and reply to every cold outreach message.

My mind is blown!

AI Secretary and the folks @genspark_ai will start printing money!

You can try this out here:

Check their announcement video and you'll see some of the crazy things it can do for you. genspark.ai

The first obvious way I've been using AI Secretary:

100x better email search.

For example, I just asked it to "show me the last 3 emails asking for an invoice for the Machine Learning School cohort."

I also asked it to label every "email containing feedback about the cohort."

Read 6 tweets

Santiago

@svpino

Jun 5, 2025

You can now have a literal army of coding interns working for you while you sleep!

Remote Agent is now generally available. This is how we all get to experience what AI is really about.

Here is what you need to know:

Remote Agent is a coding agent based on @augmentcode. They were gracious enough to partner with me on this post.

Remote Agent:

• Runs in the cloud
• Works autonomously
• Can handle small tasks from your backlog

Here is a link to try it out: fnf.dev/4jobOrw

If you have a list of things you've always wanted to solve, let an agent do them:

• Refactor code and ensure tests still run
• Find and fix bugs
• Close open tickets from your backlog
• Update documentation
• Write tests for untested code

Read 5 tweets

Santiago

@svpino

Jun 4, 2025

Knowledge graphs are infinitely better than vector search for building the memory of AI agents.

With five lines of code, you can build a knowledge graph with your data.

When you see the results, you'll never go back to vector-mediocrity-land.

Here is a quick video:

Cognee is open-source and outperforms any basic vector search approach in terms of retrieval relevance.

• Easy to use
• Reduces hallucinations (by a ton!)
• Open-source

Here is a link to the repository: github.com/topoteretes/co…

Here is the paper explaining how Cognee works and achieves these results:

arxiv.org/abs/2505.24478

Read 4 tweets

Santiago

@svpino

May 26, 2025

Cursor, WindSurf, and Copilot suck with Jupyter notebooks. They are great when you are writing regular code, but notebooks are a different monster.

Vincent is an extension fine-tuned to work with notebooks.

10x better than the other tools!

Here is a quick video:

You can try Vincent for free. Here is a link to the extension:

It works with any of the VSCode forks, including Cursor and Windsurf. The free plan will give you enough to test it out.marketplace.visualstudio.com/items?itemName…

The extension will feel familiar to you:

• You can use it with any of the major models (GPT-X, Gemini, Claude)
• It has an option to Chat and Edit with the model
• It has an Agent mode to make changes to the notebook autonomously

But the killer feature is the Report View.

Read 4 tweets

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Share this page!

Enter URL or ID to Unroll

Santiago

Try unrolling a thread yourself!

More from @svpino

Santiago

Santiago

Santiago

Santiago

Santiago

Santiago

Did Thread Reader help you today?

Don't want to be a Premium member but still want to support us?

Send Email!