Santiago (@svpino)

Typefully

Santiago

@svpino

I write about Artificial Intelligence and sometimes it's good.

2 years ago

•

View on X

ChatGPT built all of my code

Open this if you want to see how ChatGPT built all my code.

Disclaimer: I build Machine Learning models for a living. I know what questions to ask, and I can spot mistakes in ChatGPT's suggestions. ChatGPT is an incredible tool, but you must understand how to use it properly. Let's get started!

2 years ago

•

View on X

11 ways you can use ChatGPT to write code

11 ways ChatGPT saves me hours of work every day, and why you'll never outcompete those who use AI effectively. A list for those who write code:

2 years ago

•

View on X

Everything you need to know about the batch size

The batch size is one of the most influential parameters in the outcome of a neural network. Here is everything you need to know about the batch size when training a neural network:

2 years ago

•

View on X

Non-linearities

Here are the pictures of two different problems. Two classes. We want to use a neural network to solve these problems. What's the difference between them?

2 years ago

•

View on X

Early stopping

The first problem you face when starting with machine learning: Finding the perfect balance between training for too long or not training enough. Either one and your model will be trash. Here is the simplest and one of the most effective ways to work around this:

First of all, remember this: • Overfitting will likely happen if you train for too long. • Underfitting will likely happen if you don't train long enough. It's not about time, but about number of iterations—or epochs. We need a way to find the correct number.

2 years ago

•

View on X

Step by step guide to building your first deep learning model

This is a step-by-step guide to building your first deep learning model. Let's get started:

Building the model is essential, but it's just the beginning. I want to give you everything you need to understand what's going on: • A way to make changes • A way to experiment • A way to keep track of everything you did We are going to use a neat tool for that.

2 years ago

•

View on X

Model monitoring

A lesson some people learn too late: Building a machine learning system is not like building regular software. But unless you've done it before, you'd think it's all pretty much the same. Here is a reason they are different and what you can do about it:

For the most part, regular software looks like this: • Build once • Run forever* I know there's no such thing as *forever*. Things change all the time. But this rate of change pales in comparison with machine learning systems. Here is an example:

2 years ago

•

View on X

The issue with replacing missing values in your dataset

Everyone knows they need to replace missing values in their dataset. Most people, however, miss one critical step. Here is what you aren't doing and how you can fix it:

I'll start with an example. A company surveys a bunch of people. Some people leave one particular question unanswered. When we collect the data, and before using it to build a model, we must take care of these missing values.

2 years ago

•

View on X

Test-Time Augmentation

I'm sure you've used data augmentation before. Most people think of data augmentation as a technique to improve their model during training. This is true, but they are missing something. Here's a brilliant approach to improve the predictions of your model:

Let's start with a quick definition of data augmentation: Starting from an initial dataset, you can generate synthetic copies of each sample that will make a model resilient to variations in the data. This is awesome. But there's more we can do with it.

2 years ago

•

View on X

Hyperparameters

I've helped hundreds of people start with machine learning. Everyone asks me the same, fundamental question. But they all hate my answer. Engineers even more. Let me try again, but this time I'll show you a few lines of code that will 10x your process:

People always ask: "How do you know what to do now?" The answer is simple, but nobody likes to hear it: "Well, you don't know." After a few seconds, I follow up: "You need to experiment to find what works best." Here is the reality they don't want to hear about:

Write & schedule, effortlessly

Publish anywhere

AI ideas and rewrites

Turn your tweets & threads into a social blog

Powerful analytics to grow faster

Never run out of ideas

Share drafts & leave comments

Create giveaways with Auto-DMs

Schedule with one click

Pick the perfect time

Boost your content

Check the analytics that matter

Build your audience with insights that make sense.

Writing prompts & personalized post ideas

Break through writer's block with great ideas and suggestions.

Never run out of ideas

Use AI for personalized suggestions

Flick through topics

Share your drafts

Add comments

Control user access

Build an automated post machine

Our Zapier integration enables countless no-code workflows.

ChatGPT built all of my code

11 ways you can use ChatGPT to write code

Everything you need to know about the batch size

Non-linearities

Early stopping

Step by step guide to building your first deep learning model

Model monitoring

The issue with replacing missing values in your dataset

Test-Time Augmentation

Hyperparameters

Write better contentGrow your audience faster

Built for 𝕏∙LinkedIn∙Bluesky∙Threads. Powered by AI

Write & schedule, effortlessly

Publish anywhere

AI ideas and rewrites

Turn your tweets & threads into a social blog

Powerful analytics to grow faster

Never run out of ideas

Share drafts & leave comments

Create giveaways with Auto-DMs

Creators love Typefully

180,000+ creators and teams chose Typefully to curate their Twitter presence.

Queue your content in seconds

Write, schedule and boost your tweets - with no need for extra apps.

Schedule with one click

Pick the perfect time

Boost your content

Start creating a content queue.

Write once, publish everywhere

We natively support multiple platforms, so that you can expand your reach easily.

Check the analytics that matter

Build your audience with insights that make sense.

Writing prompts & personalized post ideas

Break through writer's block with great ideas and suggestions.

Never run out of ideas

Use AI for personalized suggestions

Flick through topics

Write, edit, and track tweets together

Write and publish with your teammates and friends.

Share your drafts

Add comments

Control user access

Build an automated post machine

Our Zapier integration enables countless no-code workflows.

Ready to write better content and grow your audience?

ChatGPT built all of my code

11 ways you can use ChatGPT to write code

Everything you need to know about the batch size

Non-linearities

Early stopping

Step by step guide to building your first deep learning model

Model monitoring

The issue with replacing missing values in your dataset

Test-Time Augmentation

Hyperparameters

Write better content
Grow your audience faster