Santiago
@svpino.com
I help companies build Machine Learning • I run http://ml.school. • Posts about what I learn along the way.
Everyone wants to use agents for everything, but a set of if/else/for/while statements still wins 9/10 times.
October 25, 2025 at 7:27 PM
Everyone wants to use agents for everything, but a set of if/else/for/while statements still wins 9/10 times.
I'm adding this label to the software I sell:
"Every line of code in this product was written, reviewed, and approved by a human who understands, guarantees, and stands behind it."
"Every line of code in this product was written, reviewed, and approved by a human who understands, guarantees, and stands behind it."
October 6, 2025 at 12:15 PM
I'm adding this label to the software I sell:
"Every line of code in this product was written, reviewed, and approved by a human who understands, guarantees, and stands behind it."
"Every line of code in this product was written, reviewed, and approved by a human who understands, guarantees, and stands behind it."
Google: "Our productivity has increased 10% thanks to AI."
Random Internet User: "Skill Issue! We are 100x faster!"
This is a tough one: I'm not sure who to believe here.
Random Internet User: "Skill Issue! We are 100x faster!"
This is a tough one: I'm not sure who to believe here.
October 5, 2025 at 12:10 PM
Google: "Our productivity has increased 10% thanks to AI."
Random Internet User: "Skill Issue! We are 100x faster!"
This is a tough one: I'm not sure who to believe here.
Random Internet User: "Skill Issue! We are 100x faster!"
This is a tough one: I'm not sure who to believe here.
I told a client the code behind the project I was selling them was 100% AI-free.
He loved it.
I'll do it again.
He loved it.
I'll do it again.
October 4, 2025 at 12:17 PM
I told a client the code behind the project I was selling them was 100% AI-free.
He loved it.
I'll do it again.
He loved it.
I'll do it again.
I've been uploading screenshots of my investment allocation to ChatGPT and asking where to invest a specific amount.
I've been doing this for about a year.
10/10 recommend.
I've been doing this for about a year.
10/10 recommend.
October 3, 2025 at 7:21 PM
I've been uploading screenshots of my investment allocation to ChatGPT and asking where to invest a specific amount.
I've been doing this for about a year.
10/10 recommend.
I've been doing this for about a year.
10/10 recommend.
Writing tests is a superpower, especially now with agentic coding.
Every time I ask Claude Code to build something, I get it to run my test suite:
1. It writes the code
2. Runs my test suite
3. Identifies regressions and fixes them
4. Repeats
1/2
Every time I ask Claude Code to build something, I get it to run my test suite:
1. It writes the code
2. Runs my test suite
3. Identifies regressions and fixes them
4. Repeats
1/2
October 2, 2025 at 12:15 PM
Writing tests is a superpower, especially now with agentic coding.
Every time I ask Claude Code to build something, I get it to run my test suite:
1. It writes the code
2. Runs my test suite
3. Identifies regressions and fixes them
4. Repeats
1/2
Every time I ask Claude Code to build something, I get it to run my test suite:
1. It writes the code
2. Runs my test suite
3. Identifies regressions and fixes them
4. Repeats
1/2
You should stop treating agents like humans.
This has probably been one of the biggest unlocks for me over the past few months in terms of building agents.
I see people giving agents personalities, goals, and even titles.
But agents aren't people — they are functions with context windows.
This has probably been one of the biggest unlocks for me over the past few months in terms of building agents.
I see people giving agents personalities, goals, and even titles.
But agents aren't people — they are functions with context windows.
October 1, 2025 at 3:02 PM
You should stop treating agents like humans.
This has probably been one of the biggest unlocks for me over the past few months in terms of building agents.
I see people giving agents personalities, goals, and even titles.
But agents aren't people — they are functions with context windows.
This has probably been one of the biggest unlocks for me over the past few months in terms of building agents.
I see people giving agents personalities, goals, and even titles.
But agents aren't people — they are functions with context windows.
I'm working with a huge company on their data preparation pipeline, and they are running a 9-step data processing pipeline.
This all happens before their data is ready for training. There's a lot of code here and considerable complexity.
1/4
This all happens before their data is ready for training. There's a lot of code here and considerable complexity.
1/4
October 1, 2025 at 12:20 PM
I'm working with a huge company on their data preparation pipeline, and they are running a 9-step data processing pipeline.
This all happens before their data is ready for training. There's a lot of code here and considerable complexity.
1/4
This all happens before their data is ready for training. There's a lot of code here and considerable complexity.
1/4
Python is the best language in the world.
Yes, Python is slower than other languages, but I don't care because most of my work doesn't require it to be faster.
Python is fast enough for what I need, and fast enough for most people out there.
Yes, Python is slower than other languages, but I don't care because most of my work doesn't require it to be faster.
Python is fast enough for what I need, and fast enough for most people out there.
September 30, 2025 at 3:10 PM
Python is the best language in the world.
Yes, Python is slower than other languages, but I don't care because most of my work doesn't require it to be faster.
Python is fast enough for what I need, and fast enough for most people out there.
Yes, Python is slower than other languages, but I don't care because most of my work doesn't require it to be faster.
Python is fast enough for what I need, and fast enough for most people out there.
Yesterday, I posted that large language models are non-deterministic, and people went bonkers.
People called me stupid, asked me to go back to school, and used so many other names I can't remember.
Today, I want to elaborate.
1/9
People called me stupid, asked me to go back to school, and used so many other names I can't remember.
Today, I want to elaborate.
1/9
September 30, 2025 at 1:04 PM
Yesterday, I posted that large language models are non-deterministic, and people went bonkers.
People called me stupid, asked me to go back to school, and used so many other names I can't remember.
Today, I want to elaborate.
1/9
People called me stupid, asked me to go back to school, and used so many other names I can't remember.
Today, I want to elaborate.
1/9
Building software that works is very easy… as long as you ignore all the hard parts.
January 19, 2025 at 2:01 PM
Building software that works is very easy… as long as you ignore all the hard parts.
If someone presents themselves as a "Programmer" and somebody else does it as a "Software Engineer," would you consider them equally capable?
Do you see a fundamental difference between a Programmer and a Software Engineer?
Do you see a fundamental difference between a Programmer and a Software Engineer?
January 15, 2025 at 1:15 PM
If someone presents themselves as a "Programmer" and somebody else does it as a "Software Engineer," would you consider them equally capable?
Do you see a fundamental difference between a Programmer and a Software Engineer?
Do you see a fundamental difference between a Programmer and a Software Engineer?
The final 20% of the work always takes 80% of the total effort.
January 11, 2025 at 6:05 PM
The final 20% of the work always takes 80% of the total effort.
This guy freaked out when he tried a model much dumber than GPT 3.5. He ended up losing his job.
He was an engineer and thought the model was sentient.
Imagine what will happen when 99.99% of the world population uses one of these models for the first time.
He was an engineer and thought the model was sentient.
Imagine what will happen when 99.99% of the world population uses one of these models for the first time.
January 6, 2025 at 6:23 PM
This guy freaked out when he tried a model much dumber than GPT 3.5. He ended up losing his job.
He was an engineer and thought the model was sentient.
Imagine what will happen when 99.99% of the world population uses one of these models for the first time.
He was an engineer and thought the model was sentient.
Imagine what will happen when 99.99% of the world population uses one of these models for the first time.
Anyone can learn to code, especially now with AI.
But it's still hard to find good solutions to difficult problems.
Stop obsessing about languages, libraries, frameworks, and code. They won't make a difference.
Your brain will.
But it's still hard to find good solutions to difficult problems.
Stop obsessing about languages, libraries, frameworks, and code. They won't make a difference.
Your brain will.
January 5, 2025 at 6:44 PM
Anyone can learn to code, especially now with AI.
But it's still hard to find good solutions to difficult problems.
Stop obsessing about languages, libraries, frameworks, and code. They won't make a difference.
Your brain will.
But it's still hard to find good solutions to difficult problems.
Stop obsessing about languages, libraries, frameworks, and code. They won't make a difference.
Your brain will.
There are *zero* successful software engineers who have only used one language in their careers.
Zero.
Most have used a dozen languages or more.
Programming languages don't matter. They have no bearing on how valuable you are.
And more importantly, people who pay don't care.
Zero.
Most have used a dozen languages or more.
Programming languages don't matter. They have no bearing on how valuable you are.
And more importantly, people who pay don't care.
January 2, 2025 at 6:05 PM
There are *zero* successful software engineers who have only used one language in their careers.
Zero.
Most have used a dozen languages or more.
Programming languages don't matter. They have no bearing on how valuable you are.
And more importantly, people who pay don't care.
Zero.
Most have used a dozen languages or more.
Programming languages don't matter. They have no bearing on how valuable you are.
And more importantly, people who pay don't care.
It's been 24 months since people told me my job was dead for real.
(Coincidentally, these have been the best 24 months of my professional career.)
Stop paying attention to the hype. Keep investing in yourself.
(Coincidentally, these have been the best 24 months of my professional career.)
Stop paying attention to the hype. Keep investing in yourself.
January 2, 2025 at 1:52 PM
It's been 24 months since people told me my job was dead for real.
(Coincidentally, these have been the best 24 months of my professional career.)
Stop paying attention to the hype. Keep investing in yourself.
(Coincidentally, these have been the best 24 months of my professional career.)
Stop paying attention to the hype. Keep investing in yourself.
Do you really think “Project Managers” will survive AI?
Really?
So many people in my replies seem to think Projeft Managers will be immune to AI. They are even recommending engineers to pivot.
Really?
So many people in my replies seem to think Projeft Managers will be immune to AI. They are even recommending engineers to pivot.
December 31, 2024 at 7:26 PM
Do you really think “Project Managers” will survive AI?
Really?
So many people in my replies seem to think Projeft Managers will be immune to AI. They are even recommending engineers to pivot.
Really?
So many people in my replies seem to think Projeft Managers will be immune to AI. They are even recommending engineers to pivot.
With AI improving at lightning speed, I think education is more important than it's ever been.
December 30, 2024 at 9:10 PM
With AI improving at lightning speed, I think education is more important than it's ever been.
Every developer should consider pivoting to AI/ML.
There are infinite opportunities to start enhancing what you're building with AI.
Don't stay stuck for too long. Be aggressive with this. Things are moving fast.
There are infinite opportunities to start enhancing what you're building with AI.
Don't stay stuck for too long. Be aggressive with this. Things are moving fast.
December 30, 2024 at 2:13 PM
Every developer should consider pivoting to AI/ML.
There are infinite opportunities to start enhancing what you're building with AI.
Don't stay stuck for too long. Be aggressive with this. Things are moving fast.
There are infinite opportunities to start enhancing what you're building with AI.
Don't stay stuck for too long. Be aggressive with this. Things are moving fast.
Slow unit tests are better than too many mocks.
December 29, 2024 at 6:15 PM
Slow unit tests are better than too many mocks.
This is a 10x move here. One of my favorite ways to leverage models.
December 29, 2024 at 4:14 PM
This is a 10x move here. One of my favorite ways to leverage models.
I did not visit StackOverflow in 2024.
December 28, 2024 at 3:02 PM
I did not visit StackOverflow in 2024.
Almost every person I've heard complaining about the job market has nothing to show to demonstrate their qualifications.
They have no past projects they can share, no one to vouch for them, no publications, no social presence. Nothing.
Words are cheap. Show me what you've done.
They have no past projects they can share, no one to vouch for them, no publications, no social presence. Nothing.
Words are cheap. Show me what you've done.
December 27, 2024 at 3:23 PM
Almost every person I've heard complaining about the job market has nothing to show to demonstrate their qualifications.
They have no past projects they can share, no one to vouch for them, no publications, no social presence. Nothing.
Words are cheap. Show me what you've done.
They have no past projects they can share, no one to vouch for them, no publications, no social presence. Nothing.
Words are cheap. Show me what you've done.
My favorite all-time computer ever has been the MacBook Pro M1 Pro.
I have an M3 Max and an M1 Pro. Of course, the M3 is better on every metric, but there's something I can't describe about the M1 Pro that makes it special for me.
I have an M3 Max and an M1 Pro. Of course, the M3 is better on every metric, but there's something I can't describe about the M1 Pro that makes it special for me.
December 26, 2024 at 9:07 PM
My favorite all-time computer ever has been the MacBook Pro M1 Pro.
I have an M3 Max and an M1 Pro. Of course, the M3 is better on every metric, but there's something I can't describe about the M1 Pro that makes it special for me.
I have an M3 Max and an M1 Pro. Of course, the M3 is better on every metric, but there's something I can't describe about the M1 Pro that makes it special for me.