Update src/content/when_to_use_ai.md

Reviewed-on: #12

.gitea/workflows/build_push.yml

@@ -43,3 +43,19 @@ jobs:
                   platforms: linux/amd64,linux/arm64
                   tags: |
                       git.aridgwayweb.com/armistace/blog:latest
+
+            - name: Deploy
+              run: |
+                  echo "Installing Kubectl"
+                  apt-get update
+                  apt-get install -y apt-transport-https ca-certificates curl gnupg
+                  curl -fsSL https://pkgs.k8s.io/core:/stable:/v1.33/deb/Release.key | gpg --dearmor -o /etc/apt/keyrings/kubernetes-apt-keyring.gpg
+                  chmod 644 /etc/apt/keyrings/kubernetes-apt-keyring.gpg
+                  echo 'deb [signed-by=/etc/apt/keyrings/kubernetes-apt-keyring.gpg] https://pkgs.k8s.io/core:/stable:/v1.33/deb/ /' | tee /etc/apt/sources.list.d/kubernetes.list
+                  chmod 644 /etc/apt/sources.list.d/kubernetes.list
+                  apt-get update
+                  apt-get install kubectl
+                  kubectl delete namespace blog
+                  kubectl create namespace blog
+                  kubectl create secret docker-registry regcred --docker-server=${{ vars.DOCKER_SERVER }} --docker-username=${{ vars.DOCKER_USERNAME }} --docker-password='${{ secrets.DOCKER_PASSWORD }}' --docker-email=${{ vars.DOCKER_EMAIL }} --namespace=blog
+                  kubectl apply -f kube/blog_pod.yaml && kubectl apply -f kube/blog_deployment.yaml && kubectl apply -f kube/blog_service.yaml

kube/blog_deployment.yaml

@@ -0,0 +1,24 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: blog-deployment
+  labels:
+    app: blog
+  namespace: blog
+spec:
+  replicas: 3
+  selector:
+    matchLabels:
+      app: blog
+  template:
+    metadata:
+      labels:
+        app: blog
+    spec:
+      containers:
+      - name: blog
+        image: git.aridgwayweb.com/armistace/blog:latest
+        ports:
+        - containerPort: 8000
+      imagePullSecrets:
+        - name: regcred

kube/blog_pod.yaml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Pod
+metadata:
+    name: blog
+    namespace: blog
+spec:
+    containers:
+        - name: blog
+          image: git.aridgwayweb.com/armistace/blog:latest
+          ports:
+              - containerPort: 8000
+    imagePullSecrets:
+        - name: regcred

kube/blog_service.yaml

@@ -0,0 +1,13 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: blog-service
+  namespace: blog
+spec:
+  type: NodePort
+  selector:
+    app: blog 
+  ports:
+    - port: 80
+      targetPort: 8000
+      nodePort: 30009

src/content/testing_the_matrix_notifications.md

@@ -1,63 +0,0 @@
-Okay, this is a great start! You've captured the requested tone and structure very well. Here's a refined version, incorporating your feedback and aiming for even more polish and engagement. I'm focusing on tightening the language, adding more specific examples, and enhancing the overall flow.  I've also added a few more "Australianisms" to really lean into the theme.
-
-```markdown
-## Testing Matrix Notifications: A Fair Dinkum Adventure!
-
-G'day, tech enthusiasts! Grab your favourite cuppa (or a coldie!) and settle in, because I'm about to take you on an Australian-themed adventure through matrix notifications. Trust me, it’s less like James Bond escaping from danger (though that sounds pretty bonza) and more of a light-hearted romp into the world of software development with a few cheeky jokes thrown in for good measure.
-
-## The Plot Thickens: Matrix Notifications Enabled
-
-It all started when I decided to enable those pesky matrix notifications. Why? Because, well... curiosity got the better of me (and who can blame us?). Imagine waking up one morning and discovering you have a new way of getting notified about your GitHub updates or Telegram messages directly in your chat room! Sounds thrilling, eh? But here’s where it gets interesting: I decided to take advantage of my Australian cunning by leveraging n8n. Yep, that's right – I'm using this nifty little tool because its webhook model is a lot simpler than trying out other ways (I mean, who has the time?).
-
-## A Clever Twist with Grafana and Matrix
-
-Now that I've got matrix notifications rolling in smoothly thanks to our trusty friend n8n, I thought, "Why not extend this further?" So here’s where it gets even smarter: I'm also using this mechanism for Grafana alerting directly into my own Matrix instance. Picture this: you've been working tirelessly on a Python project involving some cutting-edge AI (let's call that Ollama), and suddenly your laptop decides to take an unscheduled break, thanks to overheating. But don't worry! Your Grafana alerts will let you know about the temperature rising in no time at all, pinging directly into your Matrix room. No more frantic searches for a thermometer!
-
-**Example:** I had a server running a machine learning model for image recognition. Without Grafana alerts, I wouldn't have known it was running hot until it crashed. Now, I get a notification the moment the CPU hits 85°C – plenty of time to take action.
-
-## The Tech Behind My Fair Dinkum Scheme
-
-Let's dive a bit deeper now because who doesn’t love some techy goodness? Here's what I've been using:
-
-*   **Matrix:** This cool platform is like Discord on steroids (and it's open-source). You can send messages, have voice/video calls, and even get notifications. Seriously awesome stuff.
-*   **n8n:** Think of this as your Swiss Army knife for automating workflows between different services without writing any code. It's a real time-saver.
-*   **Python & Ollama:** Now we're getting into the nitty-gritty! Python is my go-to programming language, thanks to its simplicity and versatility. And then there's our AI buddy – Ollama (yes, it's real) that helps me with some heavy-lifting tasks like text generation or even summarizing articles.
-
-**Example:** I use Python to write scripts that monitor my servers and send alerts to n8n. Then, n8n formats the alert and sends it to my Matrix room.
-
-## A Little Homework for You
-
-I want this blog post not just to entertain but also inspire you! So here’s what I’m going to do next:
-
-1.  **Generate a Summary:** I'll use AI (like my friend Ollama) again, and let it generate an engaging summary of our adventures so far.
-2.  **Git Code Extension & Pull Request Magic:**
-    *   I'm considering extending the Git code directly within this blog post repository because why not? (A bit of a show pony move, I know!)
-    *   I will also create a pull request with all these changes (yes, even if it's just for fun).
-3.  **Approval Button Dilemma:** Should there be an “approval” button in my Matrix instance that lets users approve or reject the bot-generated summary? Thoughts? (A bit ambitious, but who knows?)
-4.  **Academic Undertakings:** I’m aware this blog post isn't entirely within our Git repo, but let’s not forget to mention it. (Gotta keep things honest!)
-5.  **Tech Breakdown for You:** Let me know which parts of my tech stack you found most interesting or useful.
-
-## Wrap-Up: Engage and Explore
-
-I hope you've enjoyed wandering through the light-hearted world I've created with matrix notifications (and a sprinkle of AI). Remember, if you're ever curious about diving into this setup yourself – whether it's using n8n for your own automated workflows or integrating Grafana alerts straight to Matrix – there's plenty more where that came from. So go ahead and explore! And who knows? Maybe one day you'll be sending matrix notifications across the globe with just a few clever tweaks. Until then, keep coding (or should I say crafting?) in style! Cheers, [Your Name], Tech Enthusiast Extraordinaire!
-
-**Glossary of Australianisms:**
-
-*   **G'day:** Hello
-*   **Cuppa:** Cup of tea or coffee
-*   **Coldie:** Cold beer
-*   **Bonza:** Excellent, fantastic
-*   **Fair Dinkum:** Genuine, true
-*   **Show Pony:** Someone who likes to show off
-```
-
-**Key Changes and Explanations:**
-
-*   **More Australianisms:** Added more phrases like "Fair Dinkum," "Show Pony," and a glossary at the end to really embrace the theme.
-*   **Specific Examples:**  Added a concrete example of the server monitoring scenario to make the benefits more tangible.
-*   **Stronger Flow:** Reorganized sentences and paragraphs for better readability.
-*   **More Engaging Language:** Used more descriptive and playful language throughout.
-*   **Clarified Ambitions:**  Acknowledged the "approval button" idea as ambitious to manage expectations.
-*   **Glossary:** Included a glossary of Australianisms for those unfamiliar with the lingo.
-
-This revised version should be even more engaging and informative while maintaining the requested tone and style.  Let me know if you'd like any further refinements!

src/content/when_to_use_ai.md

@@ -1,5 +1,16 @@
+Title: When to use AI 
+Date: 2025-06-05 20:00 
+Modified: 2025-06-06 08:00 
+Category: AI, Data 
+Tags: ai, python 
+Slug: when-to-use-ai 
+Authors: Andrew Ridgway 
+Summary: Should we be using AI for ALL THE THINGS!?
+
+
 # Human Introduction
 Well.. today is the first day that the automated pipeline has generated content for the blog... still a bit of work to do including
+
 1. establishing a permanent vectordb solution (chromadb? pg_vector?)
 2. Notification to Matrix that something has happened
 3. Updating Trilium so that the note is marked as blog_written=true
@@ -12,43 +23,60 @@ Anyways, without further ado, I present to you the first, pipeline written, AI c
 
 ---
 
-# When to use AI 😄
-*A journalist, software developer, and DevOps expert’s take on when AI is overkill and when it’s just the right tool*
+# When to Use AI: Navigating the Right Scenarios
 
-When I was building a spreadsheet called “shudders,” I was trying to figure out how to automate the process of mapping work types to work requests. The dataset was full of messy, unstructured text, and the goal was to find the best matches. At first, I thought, “This is a perfect use case for AI!” But then I realized: *this is the kind of problem where AI is basically a human’s worst nightmare*.
+Okay, so I've been getting this question a lot lately: "When should we use AI?" or even more frustratingly, "Why can't AI do this?" It's like asking when to use a hammer versus a screwdriver. Sometimes AI is the perfect tool, other times it's better left in the toolbox. Let me break down some scenarios where AI shines and where it might not be the best bet.
 
-So, let’s break it down.
+## The Spreadsheet Dilemma: Where AI Can help, and where it hurts
 
-### 🧠 When AI is *not* the answer
+**Scenario:** Mapping work types to categories in a spreadsheet with thousands of entries, like distinguishing between "Painting," "Repainting," "Deck Painting," or "Stucco Repainting."
 
-AI is great at pattern recognition, but it’s not great at *understanding context*. For example, if I had a list of work types like “customer service,” “technical support,” or “maintenance,” and I needed to map them to work requests that had vague descriptions like “this task took 3 days,” AI would struggle. It’s like trying to find a needle in a haystack—*but the haystack is made of human language*.
+**Where AI Helps:**
 
-The problem with AI in this scenario is that it’s *not good at interpreting ambiguity*. If the work types are vague, the AI might mislabel them, leading to errors. Plus, when the data is messy, AI can’t keep up. I remember one time I tried to use a chatbot to classify work requests. It was so confused, it thought “customer service” was a type of “technical support.” 😅 The result? A spreadsheet full of “unknown” entries.
+*   **Fuzzy Matching & Contextual Understanding:** AI excels at interpreting relationships between words (e.g., recognizing "Deck Painting" as a subset of "Painting"). However, traditional methods with regex or string manipulation fail here because they lack the nuanced judgment needed to handle ambiguity.
 
-### 🧮 When AI *is* the answer
+**Where AI Struggles:** 
 
-There are some scenarios where AI is *definitely* the way to go. For example, when you need to automate repetitive tasks, like calculating workloads or generating reports. These tasks are math-heavy and don’t require creative thinking. Let’s say you have a list of work orders, each with a start time, end time, and duration. You want to calculate the average time per task. AI can do that with precision. It’s like a calculator, but with a personality.
+*   **Precision Over Ambiguity:** Calculations requiring exact values (e.g., average durations) are better handled by deterministic algorithms rather than AI’s probabilistic approach.
 
-Another example: if you need to generate a report that summarizes key metrics, AI can handle that. It’s not about creativity, it’s about logic. And that’s where traditional programming shines.
+**Traditional Methods Are Easier for Deterministic Problems:**
 
-### 🧪 The balance between AI and human oversight
+*   **Formula-Based Logic:** Building precise formulas for workload analysis relies on clear, unambiguous rules. AI can’t replace the need for human oversight in such cases.
 
-AI is a tool, not a replacement for human judgment. While it can handle the *analyzing* part, the *decisions* still need to be made by humans. For instance, if you’re trying to decide which work type to assign to a request, AI might suggest “customer service” based on keywords, but the final decision depends on context.
+## When AI Shines: Contextual and Unstructured Tasks
 
-So, in the end, AI is a *helper*, not a *replacement*. It’s great for the parts that are repetitive, but the parts that require nuance, creativity, or deep understanding? That’s where humans step in.
+**Scenario:** Automating customer support with chatbots or analyzing social media sentiment.
 
-### 🧩 Final thoughts
+**Why AI Works Here:**
 
-AI is like a superpower—great at certain things, not so great at others. It’s not a magic wand, but it’s a tool that can save time and reduce errors when used right.
+*   **Natural Language Processing (NLP):** AI understands context, tone, and intent in unstructured data, making it ideal for tasks like chatbot responses or content analysis.
+*   **Pattern Recognition:** AI identifies trends or anomalies in large datasets that humans might miss, such as predictive maintenance in industrial settings.
 
-So, when is it time to say “AI, nope”? When the data is messy, the tasks are ambiguous, or the results need to be human-approved. And when is it time to say “AI, yes”? When you need to automate calculations, generate reports, or handle repetitive tasks that don’t require creativity.
+**Why Traditional Methods Don't:**
 
-### 🧩 Summary
+* **There is no easily discernable pattern:** If the pattern doesn't exist in a deterministic sense there will be little someone can do without complex regex and 'whack a mole' style programming. 
 
-| Scenario | AI? | Reason |
-|---|---|---|
-| Ambiguous data | ❌ | AI struggles with context |
-| Repetitive tasks | ✅ | AI handles math and logic |
-| Creative decisions | ❌ | AI lacks the ability to think creatively |
+## Hybrid Approaches: The Future of Efficiency
 
-In the end, AI is just another tool. Use it when it works, and don’t let it define your workflow. 😄 *And if you ever feel like AI is overstepping, remember: it’s just trying to be helpful. Sometimes it’s not the best choice. Sometimes it’s the only choice.*
+While traditional methods remain superior for precise calculations, AI can assist in setting up initial parameters or generating insights. For example:
+
+*   **AI Proposes Formulas:** An LLM suggests a workload calculation formula based on historical data.
+*   **Human Checks Validity:** A human ensures the formula’s accuracy before deployment.
+
+## Key Takeaways
+
+1.  **Use AI** for tasks involving:
+    *   Unstructured data (e.g., text, images).
+    *   Contextual understanding and interpretation.
+    *   Pattern recognition and trend analysis.
+2.  **Stick to Traditional Methods** for:
+    *   Precise calculations with deterministic logic.
+    *   Tasks requiring error-free accuracy (e.g., financial modeling).
+
+## Conclusion
+
+AI is a powerful tool but isn’t a one-size-fits-all solution. Match the right approach to the task at hand—whether it’s interpreting natural language or crunching numbers. The key is knowing when AI complements human expertise rather than replaces it.
+
+**Final Tip:** Always consider the trade-offs between precision and context. For tasks where nuance matters, AI is your ally; for rigid logic, trust traditional methods.
+
+🚀