Feb 03 2025
~ 6 min read
AI, it’s everywhere. You hear about it daily, whether it’s revolutionizing industries, automating tasks, or quietly embedding itself into nearly every tool you use. Either way, you probably have some feelings about it. Love it, hate it, or somewhere in between - AI isn’t going anywhere.
For many in tech, AI can feel a little… mystical. What’s an LLM? Where does all this data go? How does AI magically return exactly what I was looking for? While I won’t be diving into the nuts and bolts of AI today, I do want to convince you that if you’ve been sitting on the AI sidelines, now’s the time to get in the game.
LLM stands for Large Language Model. It’s a type of AI trained on massive amounts of text data to understand and generate human-like language.
Honestly, when I first started hearing about the rise of AI and saw what it was capable of producing, I was skeptical. I think it was during the 2024 Olympics when I kept seeing those cringey Microsoft ads where some guy would go, "Oops, I completely forgot about an important presentation I was supposed to put together today, better see what I can get produced in the next 30 minutes so I don't get fired." And then—bam! Some magical AI-generated presentation appears, wowing everyone and somehow being exactly what he needed. Not realistic at all, right? 😆
Well… you’d think. But aside from enabling procrastination (and maybe outright laziness), AI can actually produce some incredible results with very little effort, and it's way more effective than most people expect.
Love it, hate it, or somewhere in between-- AI isn’t going anywhere.
AI as Your Learning Assistant
One of the easiest and most practical ways to start using AI in your daily workflow is to learn a new skill or expand knowledge of existing skills. You can kind of think of it like YouTube or Google on steroids. Indeed, this is the future of search results, since ChatGPT is able to accurately match intent to a single focused result in in a matter of seconds. Tools like ChatGPT are able to take simple queries and help you expand on them in an intuitive way that is very friendly for learning.
Here is an example of a conversation I had recently when I was trying to learn more about inheritance in PHP.
Me: Can you clearly explain the difference between interfaces and abstract class in programming, specifically PHP?
ChatGPT:
Purpose and Use Case
Interface: Defines a contract that multiple classes can implement, ensuring they provide specific method signatures.
Abstract Class: Serves as a base class that can provide both abstract (unimplemented) and concrete (implemented) methods.
Method Implementation
Interface:
Only contains method signatures (before default methods in some languages like Java).
Implementing classes must define all methods.
Interface Example in PHP
An interface only defines method signatures, and the implementing class is required to define the methods.
<?php
// Define the interface
interface Animal {
public function makeSound();
}
// Implementing the interface in a class
class Dog implements Animal {
public function makeSound() {
echo "Woof!";
}
}
class Cat implements Animal {
public function makeSound() {
echo "Meow!";
}
}
// Testing
$dog = new Dog();
$dog->makeSound(); // Output: Woof!
$cat = new Cat();
$cat->makeSound(); // Output: Meow!Abstract Class Example in PHP
An abstract class can provide both abstract (unimplemented) methods and concrete (implemented) methods.
<?php
// Define the abstract class
abstract class Animal {
// Concrete method
public function sleep() {
echo "Sleeping...";
}
// Abstract method (must be implemented by subclasses)
abstract public function makeSound();
}
// Extending the abstract class in a subclass
class Dog extends Animal {
public function makeSound() {
echo "Woof!";
}
}
class Cat extends Animal {
public function makeSound() {
echo "Meow!";
}
}
// Testing
$dog = new Dog();
$dog->makeSound(); // Output: Woof!
$dog->sleep(); // Output: Sleeping...
$cat = new Cat();
$cat->makeSound(); // Output: Meow!
$cat->sleep(); // Output: Sleeping...As you can see - the ability to explain a concept with examples is incredibly valuable, and you can customize your to your specific specific languages or use cases to make the results even more relevant.
These are extremely useful capabilities for learners at all levels.
Problem Solving
Trying to solve a tough technical challenge and not sure where to start? No problem - just type the error message, or a description of the problem into ChatGPT and see what you get.
Here is an example of an interaction that helped me solve a very tough problem with a database that was way to big for no apparent reason the other day (I might do a deep dive on this in a future article...)
Me: I've got a plugin that appears to be making my Wordpress database really large - any ideas where to start looking?
ChatGPT: Identify Which Table Is Growing - You can run the following SQL query to find large tables:
SELECT table_name, ROUND((data_length + index_length) / 1024 / 1024, 2) AS size_mb
FROM information_schema.tables
WHERE table_schema = DATABASE()
ORDER BY size_mb DESC;From there - I was able to see that in fact, my Wordpress database itself was not growing and was actually quite small...the plot thickens....
After some more digging on the filesystem, I saw that the file "var/lib/mysql/binlog" appeared to be taking up all the space. So - back to GPT we go:
Me: "var/lib/mysql/binlog appears to be the culprit..."
ChatGPT: If /var/lib/mysql/binlog is growing rapidly, that means MySQL's binary logging is enabled and accumulating too much data.
I looked into what binary logging was for and discovered we didn’t actually need it enabled. ChatGPT then guided me through detailed steps to disable it and safely purge the files to reclaim disk space.
Incredibly cool stuff. I can't imagine how long it would've taken to figure out what was going on without this feedback.... (hours, days maybe...)
Coding
Developers, if you’re not already using a tool like GitHub Copilot (it’s built right into VS Code now), you’re missing out on an incredibly useful, time saving tool. With simple natural language prompts, you can generate the basic scaffolding for components, classes, and functions in seconds.
For example, you could type:
"Generate an HTML snippet using the latest version of Tailwind v3. It should have a heading, subheading, and a paragraph area. Make it all left-aligned and provide a reasonable amount of spacing around each element."
Boom — AI generates a structured, well-formatted block of code with sensible defaults. Want it tweaked? Just refine the prompt — adjust font sizes, tweak margins, align specific elements. Instead of manually piecing things together, you get an instant foundation to work with. That’s hours saved when testing new ideas or spinning up prototypes.
When using tools like ChatGPT or GitHub CoPilot - make sure you read the explanation of what it is generating and why. If you just blindly copy and paste or "apply" the suggested changes to your code, you are missing out on valuable information to learn about how things work, and I guarantee that will come back to bite you later.
AI Is Not a Fad — It’s a Competitive Edge
I don’t believe AI is just a passing trend. Workers who correctly leverage it will be faster, have reduced errors, and gain a serious productivity edge over those who don’t. Ignoring AI at this point is like refusing to use email because you "prefer the good old days of handwritten letters" (and by the way, I still like receiving mail from time to time too.)
Technology leaders’ expectations are evolving fast, and what was once a competitive edge is now the bare minimum. To stay ahead, you need to meet—and exceed—these new standards.
Any new technology can feel intimidating, but the best way to get past that is to jump in, experiment, and see for yourself. I have a feeling you’ll be pleasantly surprised.
share the love
The views and opinions expressed on this blog are the author's own and do not reflect those of their employer, past or present. Any content shared here is for informational purposes only and should not be taken as professional or legal advice.
The Afterburner
The conversation continues with additional thoughts, insights and commentary.AI is still capturing headlines in the news as companies big and small continue to lay-off more employees in masse, citing optimization around AI process as a primary reason.
Naturally, people are asking: what do I make of all this, and how will it reshape the global workforce?
My opinion: what grabs headlines are often the extreme ends of the spectrum, because these are what elicit the most emotional responses.
On one end, you’ve got the “AI is coming for all your jobs” crowd, stoking fear to drive attention. Tools like Cursor are held up as proof, promising to crank out full-blown AI-generated software apps with minimal human input.
On the other end, some folks write AI off entirely as the latest entry in the cyclical IT "fad", like the ".com" boom, NoSQL, cloud, blockchain, or big data.
Each of these "fads" has eventually found their grounding in sensible use cases that applied the technology properly to the appropriate business domains - to provide increased value or solve real problems.
Point being, the path forward for organizations right now is most likely somewhere in the middle of the two extremes.
We shouldn't expect AI tools like "Cursor" to build your software application for you, but can AI super-charge your teams to make better decisions, up-skill faster, and enable to solve more complex problems? Absolutely.
I think smart organizations will place their current bets in AI as a powerful force for workforce augmentation, not automation, because (at least until the dust settles), this approach maximizes value and minimizes risk.
Something I've been thinking more about is what I believe is one of the most under-discussed parts of AI: legal, compliance, and governance.
I believe the real inflection point for AI isn't only about the tech — it’s about how laws and regulations catch up to it. Especially in the murky gray zones where ethics and profit collide.
Like with most emerging tech, the rules are trailing behind the innovation. Companies are already deploying AI in ways that lawmakers haven’t fully wrapped their heads around yet.
That gap creates a lot of uncertainty, not only about what’s possible, but what’s going to be allowed down the line.
Here are some current headlines around AI policy making within the EU and the US.
EU
The European Union has taken a proactive approach by enacting the AI Act, which came into force on August 1, 2024. This comprehensive legal framework categorizes AI systems based on risk levels and imposes strict requirements on high-risk applications, including transparency, safety, and human oversight.Source
A critical aspect of the AI Act is its emphasis on data governance. Organizations are required to ensure data lineage, provenance tracking, and automated classification to prevent biases and unauthorized data use. Compliance challenges have highlighted the need for robust data governance frameworks to meet the Act's stringent requirements.Source
United States
In the U.S., a significant concern is the practice of "AI washing," where companies exaggerate their AI capabilities to attract investors. The U.S. Securities and Exchange Commission (SEC) has prioritized this issue, requiring companies to substantiate their AI-related claims. For instance, in 2025, the SEC took action against DocGo Inc. for misleading investors about its AI capabilities and executive credentials.Source