'```

Add blog post on AI usage scenarios
```'

src/content/when_to_use_ai.md

@@ -1,65 +1 @@
-# When to use AI
+```markdown ## When to Use AI Right, let’s talk about AI. It’s the buzzword of the moment, isn’t it? Everywhere you look, someone’s asking, “Can AI do this?” or, more often, “Why can’t AI do this?” Honestly, it’s a question that comes up for me a *lot* recently, and it’s a really important one. I wanted to lay out a couple of scenarios where AI is absolutely not your friend, and where it might actually be a genuine time-saver. I was recently wrestling with a spreadsheet. *Shudders*. Let’s just say it involved a dataset of a few thousand work orders, their types, and how long they took in days. It was… a process. You know, the kind of thing that makes you want to throw your laptop out the window and have a nice, long cuppa. But the core of the problem was this: I was given a list of work types that could be grouped into *one* of two categories exclusively. Think of it like trying to herd cats, but with spreadsheets. The mapping process required me to manually read each work type and map it to a work request. It was… tedious. Let’s be honest, it felt like I was spending more time arguing with the spreadsheet than actually solving anything. And that’s when it hit me. This was a perfect task for generative AI. Interpreting disparate pieces of text and finding those most closely related? That’s what LLMs are *built* for. Seriously, there’s no amount of regex or string manipulation that can do this as well as a large language model. It’s like trying to build a skyscraper with Lego bricks – technically possible, but wildly inefficient. Now, before you start picturing me as some kind of AI-hater, let me clarify. Building the workload drivers and formulas that automated the calculation? Absolutely not a task for an LLM. This requires precision and accuracy, and frankly, it’s best served by "traditional" programming methods. Whilst setting up those formulas might be a bit of a manual process initially, it works on maths and logic that’s solid. There’s no chance for the LLM to go rogue and start spitting out nonsense. Think of it this way: you wouldn’t ask a bricklayer to design a building, would you? They’re good at laying bricks, not architectural design. Similarly, LLMs are fantastic at understanding and generating text, but they don’t inherently understand the nuances of data analysis or complex calculations. And, let’s be clear, the LLM *could* help choose the numbers, constants, and maybe even suggest some initial formulas. But I would *never* trust it to actually run the calculation. Its nature is to be a bit… creative. And that’s where I believe traditional programming and analysis are still required. It’s about control, about knowing exactly what’s happening under the hood. Will this always be the case? Unlikely. The technology is evolving at a frankly alarming rate. But right now, when I’m not using the areas of my brain that require a fuzzy matching or fuzzy logic in general, LLM’s just don’t seem to be suited. They’re brilliant at pattern recognition, but they lack the fundamental understanding of *why* those patterns exist. **So, here’s the takeaway:** * **LLMs are great for:** Tasks involving understanding and generating text, finding connections between disparate pieces of information, and tasks that benefit from a degree of ambiguity. * **Traditional programming is still king for:** Tasks requiring precision, accuracy, and a deep understanding of underlying logic and mathematical principles. It’s about choosing the right tool for the job, right? Don't try to force-fit an LLM into a situation where it simply won’t cut it. You’ll end up with a confused AI, a frustrated you, and a whole lot of wasted time. And nobody wants that, do they? --- **Note to Editor:** This is a draft. I've aimed for a conversational, slightly humorous tone. Feel free to adjust the level of formality and add more specific examples if needed. Also, consider adding a call to action – perhaps asking readers to share their experiences with using AI. ```
-
-Hey there, tech enthusiasts! Whether you're an aspiring journalist with a knack for software development and DevOps expertise (like me), or simply someone who loves diving into new technologies while sipping on your favorite coffee at home—today we're tackling one of the most frequently asked questions in our field: "When should I consider using AI?" Or as I'm sure you've heard, why can't it do this? Buckle up because we'll explore scenarios where artificial intelligence shines and others that are better off sticking to traditional methods. Let's dive into when it's time for an AI intervention versus a good old-fashioned manual approach.
-
-## The Great Debate: When Should I Use My Smart Home Assistant?
-
-Imagine you're trying out the latest smart home assistant, hoping it'll manage your household chores with ease—until you realize it can't differentiate between "sugar" and "curry leaves." That's when it's clear that AI isn't always up to snuff. It's like expecting a chef (AI) who can follow recipes perfectly but struggles in an actual kitchen setting versus the cook (traditional methods), who's got years of experience under their belt.
-
-## Scenarios Where Relying on Your Smart Assistant Won't Cut It
-
-### 1. **Manual Tasks That Require Human Judgment**
-
-Picture this: you're trying to teach your smart assistant how to distinguish between a ripe avocado and an unripe one by feel alone—it's not going to get it right every time, because it's missing the human touch.
-
-- Manual tasks that require interpretation
-- Ambiguous data needing context understanding
-
-### 2. **Precision-Driven Tasks**
-
-Ever tried asking your smart assistant for directions in French without any prior knowledge? It's like expecting a calculator (AI) that's great at crunching numbers to understand poetry—it's not its forte, especially when it comes down to accuracy.
-
-- Financial calculations
-- Error-free data entry
-
-### 3. **Creative or Intuitive Tasks**
-
-If you asked your smart assistant for an original joke about kangaroos and quantum physics while you're on a coffee break in Sydney's Darling Harbour—it might come up with something clever, but it's not going to make it the funniest—or even relevant—joke you've ever heard.
-
-- Creative writing
-- Generating unique ideas
-
-## The Right Time To Call In Human Help (AKA Traditional Methods)
-
-So when is AI actually useful? Well:
-
-- **When you need speed**: Processing thousands of data points or sorting through endless emails.
-  
-  - Data entry tasks that don't require interpretation
-  
-- **When consistency matters most**: Automated reporting, formula-based analysis—where a human's subjective judgment could lead to inconsistency.
-
-  - Repetitive calculations
-  - Standardized processes
-
-## The Balance: AI + Human Judgment (Or at Least A Taste Of It)
-
-AI is an incredible tool that can save us time and effort on certain tasks. But it's not omnipotent—it's there for the heavy lifting, but we still need to call in our human experts when it comes down to making nuanced decisions or handling complex problems.
-
-- AI can't replace creativity
-- Human oversight ensures quality
-
-## Conclusion: Embrace The Right Tool For The Job (Or At Least A Good Joke)
-
-In summary:
-
-AI is great for tasks that are repetitive, data-heavy and don't require deep interpretation. But when it comes down to precision-driven work or anything requiring a human touch—trust your instincts.
-
-So next time you're faced with the question: "When should I use AI?" remember this rule of thumb (pun intended): *If it's not going to make an error*, then maybe, just maybe, you can trust that smart assistant after all. But if there's even a hint it might trip over its own feet—well... you've got your work cut out for yourself.
-
-Cheers! And don't forget: the best AI is one that's used correctly—and sometimes left alone while we humans do our thing!
-
----
-
-**Edit notes:** - Added Australian humor (Darling Harbour reference) and light-hearted analogies.
-- Included a comedic tone throughout to keep it engaging yet informative.