Santiago Profile picture
Apr 26, 2021 21 tweets 7 min read Read on X
20 quotes that I use as inspiration to change my life.

Print them out. Keep them close. Read them frequently. Reflect on them and the wisdom behind every word.

Let's start:

Humans are allergic to change. They love to say, "We've always done it this way." I try to fight that. That's why I have a clock on my wall that runs counterclockwise.

— Grace Hopper
With engineering, I view this year's failure as next year's opportunity to try it again.

Failures are not something to be avoided. You want to have them happen as quickly as you can so you can make progress rapidly.

— Gordon Moore
People think that computer science is the art of geniuses, but the actual reality is the opposite, just many people doing things that build on each other, like a wall of mini stones.

— Donald Knuth
Don't rest on your laurels. There's always going to be someone behind you who's going to be better than you. So you need to get out there and keep working.

— Sheila Johnson
Any fool can write code that a computer can understand. Good programmers write code that humans can understand.

— Martin Fowler
Love what you do and do what you love. Doing something new and different requires a level of drive and passion that is really hard to fake. When your heart is behind what you are doing, so much is possible.

— Tracy Sun
If you're not failing 90% of the time, then you're probably not working on sufficiently challenging problems.

— Alan Kay
"Nothing in life is to be feared, it is only to be understood. Now is the time to understand more, so that we may fear less."

— Marie Curie
It is better to do the right problem the wrong way than the wrong problem the right way.

— Richard Hamming
Dream small dreams. If you make them too big, you get overwhelmed and you don't do anything. If you make small goals and accomplish them, it gives you the confidence to go on to higher goals.

— John H. Johnson
Debugging is twice as hard as writing the code in the first place. Therefore, if you write the code as cleverly as possible, you are, by definition, not smart enough to debug it.

— Brian Kernighan
There is no recipe, there is no one way to do things — there is only your way. And if you can recognize that in yourself and accept and appreciate that in others, you can make magic.

— Ara Katz
Imagination is more important than knowledge. For knowledge is limited, whereas imagination embraces the entire world, stimulating progress, giving birth to evolution.

— Albert Einstein
Simplicity is about subtracting the obvious and adding the meaningful.

— John Maeda
If you wake up deciding what you want to give versus what you're going to get, you become a more successful person. In other words, if you want to make money, you have to help someone else make money.

— Russell Simmons
It's hard enough to find an error in your code when you're looking for it; it's even harder when you've assumed your code is error-free.

— Steve McConnell
I have not failed. I've just found 10,000 ways that won’t work.

— Thomas Edison
I always did something I was a little not ready to do. I think that's how you grow. When there's that moment of "Wow, I'm not really sure I can do this," and you push through those moments, that's when you have a breakthrough.

— Marissa Mayer
Technology is nothing. What's important is that you have a faith in people, that they're basically good and smart, and if you give them tools, they'll do wonderful things with them.

— Steve Jobs
You can do anything you want to, but you have to work at it.

— Annie Easley

• • •

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

Keep Current with Santiago

Santiago Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

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

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @svpino

Mar 31
What a week, huh?

1. Mojo 🔥 went open-source
2. Claude 3 beats GPT-4
3. $100B supercomputer from MSFT and OpenAI
4. Andrew Ng and Harrison Chase discussed AI Agents
5. Karpathy talked about the future of AI
...

And more.

Here is everything that will keep you up at night:
Mojo 🔥, the programming language that turns Python into a beast, went open-source.

This is a huge step and great news for the Python and AI communities!

With Mojo 🔥 you can write Python code or scale all the way down to metal code. It's fast!

modular.com/blog/the-next-…
Claude 3 is the best model in the market right now, overtaking GPT-4.

Claude 3 Opus is #1 in the Arena Leaderboard (beating GPT-4.)

Opus is a huge model, but Claude 3 Haiku is cheap and fast. And it's also beating GPT-4 0613!

Read 10 tweets
Mar 13
The batch size is one of the most important parameters when training neural networks.

Here is everything you need to know about the batch size:

1 of 14 Image
I trained two neural networks.

Same architecture, loss, optimizer, learning rate, momentum, epochs, and training data. Almost everything is the same.

Here is a plot of their losses.

Can you guess what the only difference is?

2 of 14 Image
It's the batch size.

The first network uses batch_size = 1.

The loss is noisy and takes a long time to train.

And every time I run it, I get completely different results. It keeps jumping around and never settles on a good solution.

3 of 14 Image
Read 14 tweets
Jan 5
I had an amazing machine learning professor.

The first thing I learned from him was how to interpret learning curves. (Probably one of the best skills I built and refined over the years.)

Let me show you 4 pictures and you'll see how this process flows:

1/5 Image
I trained a neural network. A simple one.

I plotted the model's training loss. As you can see, it's too high.

This network is underfitting. It's not learning.

I need to make the model larger.

2/5 Image
I increased the capacity of the model. The training loss is now low.

The model is not underfitting anymore, but it might be memorizing the data. I don't know yet.

I need to evaluate this model.

3/5 Image
Read 5 tweets
Dec 21, 2023
AI will be one of the most crucial skills for the next 20 years.

If I were starting today, I'd learn these:

• Python
• LLMs
• Retrieval Augmented Generation (RAG)

Here are 40+ free lessons and practical projects on building advanced RAG applications for production:

1/4
This is one of the most comprehensive courses you'll find. It covers all of LangChain and LlamaIndex.

And it's 100% FREE!

@activeloopai, @towards_AI, and @intel Disruptor collaborated with @llama_index to develop it.

Here is the link:

2/4learn.activeloop.ai/courses/rag
This is a practical course.

It focuses on state-of-the-art retrieval strategies for RAG applications in production.

You will solve problems across industries:

• Biomedical
• Legal
• Financial
• E-commerce and others!

Attached you'll see an example agent you'll build.

3/4 Image
Read 4 tweets
Oct 25, 2023
The best real-life Machine Learning program out there:

"I have seen hundreds of courses; this is the best material and depth of knowledge I've seen."

That's what a professional Software Engineer finishing my program said during class. This is the real deal.

I teach a hard-core live class. It's the best program to learn about building production Machine Learning systems.

But it's not a $9.99 online course. It's not about videos or a bunch of tutorials you can read.

This program is different.

It's 14 hours of live sessions where you interact with me, like in any other classroom. It's tough, with 30 quizzes and 30 coding assignments.

Online courses can't compete with that.

I'll teach you pragmatic Machine Learning for Engineers. This is the type of knowledge every company wants to have.

The program's next iteration (Cohort #8) starts on November 6th. The following (Cohort #9) on December 4th.

It will be different from any other class you've ever taken. It will be tough. It will be fun. It's the closest thing to sitting in a classroom.

And for the first time, the next iteration includes an additional 9 hours of pre-recorded materials to help you as much as possible!

You'll learn about Machine Learning in the real world. You'll learn to train, tune, evaluate, register, deploy, and monitor models. You'll learn how to build a system that continually learns and how to test it in production.

You'll get unlimited access to me and the entire community. I'll help you through the course, answer your questions, and help with your code.

You get lifetime access to all past and future sessions. You get access to every course I've created for free. You get access to recordings, job offers, and many people doing the job you want to do.

No monthly payments. Ever.

The link to join is in the attached image and in the following tweet.
Image
The link to join the program:
The cost to join is $385.

November and December are the last two iterations remaining at that price. The cost will go up starting in January 2024.

Today, there are around 800 professionals in the community.ml.school
Live sessions and recordings:

Sessions are live, and I recommend every student to attend if they can.

But we also record every session, and you get access to the recordings. You can watch them whenever you want.

We also have 2 office hours. They are optional but a lot of fun!
Read 8 tweets
Oct 2, 2023
AI is changing how we build software.

A few weeks ago, I talked about using AI for code reviews. Many dismissed the idea, saying AI can't help beyond trivial suggestions.

You are wrong.

Here are a few examples of what you can do with @CodiumAI's open-source pull request agent: Image
Here, the agent generated the description of a pull request.

It looks at every commit and file involved and summarizes what's happening automatically.

You can do this by using the "/describe" command. Image
Sometimes, you need a more thoughtful review of the pull request.

If you want to go deeper, use the "/review" command and have the model generate a full analysis like this.

The tool lets you control which commands will run automatically on every pull request. Image
Read 8 tweets

Did Thread Reader help you today?

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!

Follow Us!

:(