Forem: Cesar Aguirre

It might seem slower or old-school. But it forces me to stay in control

Cesar Aguirre — Tue, 19 May 2026 13:31:51 +0000

Cesar Aguirre

May 18

The One Rule I Follow to Code with AI (Without Losing My Skills)

#beginners #ai #coding #programming

Comments 4

2 min read

The One Rule I Follow to Code with AI (Without Losing My Skills)

Cesar Aguirre — Mon, 18 May 2026 05:00:00 +0000

I haven't blindly jumped on the AI hype train. But I'm no hater either.

AI is here to stay. That's why I've tried AI to offload tasks while coding.
But after a few weeks, I was so dependent I couldn't write a simple LINQ query by hand.

So I decided to stop relying too much on AI and adopted this one rule:

Use AI outside my IDE or editor.

When I'm coding, I like to think I'm a surgeon in an operating room, and AI is my assistant doctor. They hand me tools and monitor my patient, but I'm always in charge.

How to be always in charge of AI

To stay in control, I never let AI into my editor. I use it in a browser tab.

It might seem slower or old-school. Sure!
But it forces me to decompose my problem and extract relevant code for AI.
And once I have an answer, it forces me to make it work on my side.
At least, I know if the output actually works.

Just like code you find on StackOverflow or anywhere else online, don't use what AI gives you if you don't understand what it's doing.

Don't let AI touch your code directly either.

AI is faster at generating code than us. No doubt! But being a good coder isn't about typing fast. It's about estimation, collaboration, and many more skills I've included in Street-Smart Coding—The roadmap I wish I had when I was starting out.

It seems typing out code is already the old way

Cesar Aguirre — Tue, 12 May 2026 17:37:19 +0000

Cesar Aguirre

May 11

The Main Advantage Of Coding "The Old Way" Over AI-Assisted Coding

#coding #beginners #ai #programming

Comments 2

2 min read

The Main Advantage Of Coding "The Old Way" Over AI-Assisted Coding

Cesar Aguirre — Mon, 11 May 2026 05:00:00 +0000

Typing out code is already the old way.

The other day, I stumbled upon this post titled, I'm Coding By Hand.
Its subtitle got my attention: "I'm spending 3 months coding the old way." Whaaat?!

The old way of coding

The future of coding is already here.

Decades ago, we punched cards.
For so long, we've been typing out symbols inside IDEs.
That's now "the old way."

Maybe the future is AI specs via brain implants. Who knows!

What you miss when coding with AI

The post made an excellent distinction between old coding vs AI-assisted coding.

"when writing code 'by hand' I was actually doing two things: writing what I wanted and learning the codebase...if I didn't know what I wanted exactly, coding agents would be happy to make many assumptions for me. This almost always meant that I didn't learn as much, and that I wouldn't have a good grasp of the codebase."

Coding isn't just typing.

It's decoding business rules or problem constraints to then encode them into a programming language, while

Mastering its syntax and rules,
Making the new coding artifacts interact with existing ones,
Following the structure and conventions of the codebase,
Learning about the business domain,
And of course, solving the problem at hand.

Maybe with AI, we may lose some of those activities.
If AI writes 90% of code, being a polyglot isn't valuable anymore.

In the meantime, every AI-generated line of code we don't understand isn't just technical debt. It's cognitive debt.

AI is like a powerful calculator: only useful if you know the math. To help you level up your coding skills—AI-assisted coding or old school—check out Street-Smart Coding. The roadmap I wish I had starting out.

80% of the time, coding is a performance. The other 20% is doing real coding.

Cesar Aguirre — Tue, 05 May 2026 14:07:37 +0000

Cesar Aguirre

May 4

Coding For A Living Is More Performance Than Code

#discuss #coding #beginners #career

Comments 2

1 min read

Coding For A Living Is More Performance Than Code

Cesar Aguirre — Mon, 04 May 2026 05:00:00 +0000

80% of the time, coding is a performance. The other 20% is doing real coding.

Performance means Scrum ceremonies, meetings, and JIRA:

A meeting to present tickets for the next two weeks
A meeting to answer questions from the previous meeting
A meeting to watch someone enter a number in a text box. Read: poker planning and story points
Meetings to watch someone move a ticket between JIRA lanes. Read: daily meetings
A meeting about all the other meetings. Read: retrospective

And when things go sideways, the performance intensifies with more frequent meetings. Sometimes a team member's only job is running ceremonies and writing reports.

That kills the fun of coding and can make you hate it.

This happens everywhere. @sylwia-lask asked in this post if that's something that only happens at her place. Nope! Even in the best families, as we say in our hometown.

Showing progress matters more than real work. Coding is often just a side quest. A hard truth nobody tells us about.

To succeed as a coder, you need to master the ceremonies as much as the code. That's why Street-Smart Coding covers communication and collaboration. Because coding is more than typing symbols.

It's not running out of token money :P

Cesar Aguirre — Tue, 28 Apr 2026 14:13:17 +0000

Cesar Aguirre

Apr 27

The Real Problem With AI Writing All Our Code

#coding #ai #programming #vibecoding

Comments 4

2 min read

The Real Problem With AI Writing All Our Code

Cesar Aguirre — Mon, 27 Apr 2026 05:00:00 +0000

AI might promise speed and productivity. But it comes with serious issues.

The other day I found a senior coder quitting AI coding after finding out that:

AI was like a sloppy coder who bypassed tests and wrote bad code
AI had stolen all the joy of solving problems from him

After experimenting with AI, I realized I was becoming lazier than usual. Since then, I've set simple rules to avoid losing my skills.

But those aren't the biggest problems.

A failed experiment revealed a more serious problem

Recently I found out about the experiment of a team of coders that revealed a deeper problem. This one,

Veith Röthlingshöfer

Nov 3 '25

Why agents DO NOT write most of our code - a reality check

#ai #agents #programming

Comments 22

8 min read

After trying to write a feature at work only by prompting, they realized:

[Even when AI is capable of writing all of our code], a huge issue remains: I lose my mental model of the codebase.
...
Until I can trust the AI completely, I need to keep my own mental model alive. Otherwise, every time I need to do something myself feels like joining a new company.

It takes time to get familiar with a complex codebase.

At past jobs, it took me about a year to feel confident. Of course, your mileage may vary.

But when that happens, you feel like driving through familiar streets with only one hand on the wheel:

You know the architecture, the folder structure, and even a rough sketch of code blocks.
You know how modules connect and what to touch or avoid.
You can even remember file and function names.

You've built the mental models and gained all the context. Without them, you feel like walking into a dark room.

When AI writes our code, it's stealing the context and the feeling of knowing a codebase like the palm of your hand.

Use AI if you want, but be the one dictating what to do.
Draw the boundaries of the solution, then let AI fill in the details.
Be the pilot and let AI be your copilot.

When AI can handle syntax, it's time to work on skills it can't, like collaboration, clear communication, and problem-solving. That's why I wrote Street-Smart Coding, the roadmap I wish I had on my journey from junior to senior.

20+ signs you're a real programmer (using two monitors isn't one)...

Cesar Aguirre — Thu, 23 Apr 2026 15:07:04 +0000

Cesar Aguirre

Mar 24 '25

You're Not a Programmer Until...

#watercooler #discuss #programming #jokes

140

Comments 64

3 min read

If AI writes 90% of our code, becoming a polyglot coder isn't valuable anymore.

Cesar Aguirre — Tue, 21 Apr 2026 14:12:47 +0000

Cesar Aguirre

Apr 20

If AI Finally Writes 90% of Code, You Don't Need to Learn So Many Languages

#coding #beginners #programming #ai

Comments 6

2 min read

If AI Finally Writes 90% of Code, You Don't Need to Learn So Many Languages

Cesar Aguirre — Mon, 20 Apr 2026 05:00:00 +0000

We no longer need to keep learning new programming languages.

If AI writes 90% of our code, becoming a polyglot coder isn't valuable anymore.

Here's what Gergely Orosz, from The Pragmatic Engineer, says in When AI Writes All Code,

...With AI writing most of the code, the advantage of knowing several languages will become less important when any engineer can jump into any codebase and ask the AI to implement a feature – which it will probably take a decent stab at. Even better, you can ask AI to explain parts of the codebase and quickly pick up a language much faster than without AI tools.

Obsessing over learning languages didn't work for me. That was before AI.

Trying to master many languages was my biggest mistake as a new coder. Something else always made people stand out. And something else got me into trouble.

The real question is what skills matter—apart from mastering syntax

Maybe AI is making us:

Master one general-purpose language, like C or Go.
Understand core principles: problem decomposition, SOLID, and clean code.
Develop strong code-reading skills.

Or maybe we should learn one language that challenge our thinking: Haskell, LISP, or a language from a different paradigm. (Learning Java after C# doesn't teach much.)

Not because you'll use it daily, AI can generate code in "challenging" languages, but it builds stronger problem-solving skills and rewires how you think. Helpful skills for prompting LLMs.

To stand out when AI shines at coding, we need to step beyond the IDE. We need teamwork, communication, and the broader skills I cover in Street-Smart Coding. It's the roadmap I wish I had when starting out.

You're the surgeon and AI is your supporting team.

Cesar Aguirre — Thu, 16 Apr 2026 16:34:24 +0000

Surgical metaphors and documentation use cases

Cesar Aguirre

Apr 13

Two Ways to Think of AI Without Outsourcing Your Mind

#coding #beginners #ai #webdev

Comments 4

1 min read