armistace/blog
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix conflicts

Browse Source
This commit is contained in:
armistace 2025-06-06 11:32:25 +10:00
commit 8c342d994e
1 changed files with 21 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
src/content/when_to_use_ai.md
View File

@ -15,46 +15,46 @@ Well.. today is the first day that the automated pipeline has generated content
2. Notification to Matrix that something has happened
3. Updating Trilium so that the note is marked as blog_written=true
BUT it can take a note from trilium, generate drafts with mulitple agents, and then use RAG to have an editor go over those drafts.
## The Great AI Debate: When to Trust the Machine vs. When to Stick to Your Brain
I'm particularly proud of the randomness I've applied to temperature, top_p and top_k for the different draft agents. This means that each pass is giving me quite different "creativity" (as much as that can be applied to an algorithm that is essentially munging letters together that have a high probability of being together) It has created some really interesting variation for the editor to work with and getting some really interesting results.
As a journalist, software developer, and DevOps expert, I’ve spent years navigating the murky waters of AI’s “what if” scenarios. The question that keeps coming up professionally is: *“When to use AI?”* And the answer, like many things in life, is *“It depends.”* But when I’m not using my brain, I’m using my shudders. Let’s dive into the scenarios where AI isn’s the best choice—and where it *is* the best choice.
Anyways, without further ado, I present to you the first, pipeline written, AI content for this blog
## When AI is Not the Best Choice
---
### 1. **The Fuzzy Logic Dilemma**
# 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*
AI is great at handling *fuzzy logic*—like when you’re trying to figure out if a work order is “urgent” or “not urgent” based on vague descriptions. But when you’re trying to map a work type to a specific work request, AI is *not* the best choice. Imagine this: You have a dataset of work orders, each with a type (e.g., “installation,” “repair,” “maintenance”) and a duration in days. You’re trying to group these into two categories: *“high-priority”* and *“low-priority.”* The problem? The work types and work requests are *tangentially related*.
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*.
> *“I was given a list of work types that could be grouped into 1 of 2 categories exclusively.”*
> *“The problem was… the ‘work types’ and work requests were at best tangentially related.”*
So, let’s break it down.
So I had to manually read each work type and map it to a work request. It was a *shudder-inducing* task. AI, on the other hand, would have *automated* that. But it would also have *misunderstood* the relationship between the two.
### 🧠 When AI is *not* the answer
### 2. **The Math and Logic Job**
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*.
AI is great at math and logic. If you need to calculate the total time spent on a process, or create a formula that accounts for variables like labor hours, weather, or equipment downtime, AI can handle it. For example, I once built a spreadsheet that calculated potential savings in a process. The formulas were precise, and the logic was sound.
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.
> *“Traditional programming methods work on maths and logic that is sound and offers no chance for interpretation.”*
### 🧮 When AI *is* the answer
So even if AI could suggest the numbers, I’d never trust it to actually run the calculation. It’s like trusting a robot to drive a car when it’s not built for that.
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.
## When AI is the Best Choice
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.
### 1. **Finding Connections**
### 🧪 The balance between AI and human oversight
AI excels at identifying patterns and relationships within large datasets. This is invaluable for tasks like customer segmentation, fraud detection, and predictive maintenance.
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.
### 2. **Automating Repetitive 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.
Many tasks are simply too repetitive and time-consuming for humans to perform efficiently. AI-powered automation can free up valuable time and resources.
### 🧩 Final thoughts
### 3. **Suggesting Numbers or Constants**
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.
While AI shouldn't be trusted to run calculations, it can be helpful in suggesting potential numbers or constants to use in those calculations.
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.
## The Human vs. AI Divide
### 🧩 Summary
AI is good at *finding connections* and *handling ambiguity*, but it’s *not good at precision*. When you need to ensure that a calculation is accurate, or that a mapping is flawless, AI is not the best choice. And that’s where humans shine. We’re good at *seeing* the connection between two things, even if it’s not obvious. We’re good at *precision* and *accuracy*.
| Scenario | AI? | Reason |
|---|---|---|