Posts

Showing posts from June, 2025

NoOps: Will AI Eliminate Traditional DevOps?

Image
In response to a LinkedIn post I came across (If you are part of the AWS Certification & Training ). I hit the character limit 😅, so extending on that here. DevOps Automation DevOps has been trying to automate itself out of its role since its inception. That was the whole point of the role in the first place and yet still many orgs are facing: Totally custom setups and never-ending edge cases. Operational dysfunction. Multiple disjointed tools that perform the same functions. Development teams operating in silos that don't conform to the federated guidance DevOps is attempting to implement. Incomplete monitoring systems or multiple monitoring tools that don't cross communicate. Incredibly ever complex logs with vague descriptions as to what actually went wrong. Office politics where confusion exists around role and responsibility when the pipeline breaks. Current Challenges Many orgs are still: In the phase of getting away from monolithic apps into micr...

The Problem I have with AI Today

This is a rant post. The problem I have with AI has multiple layers. I'll try to cover them as best I can in this post. However, this may change over time. Premise It started with an email from Lovable. This weekend, they are doing "free credits" for this championship match among the top AI companies out there: OpenAI (ChatGPT), Anthropic (Claude/Sonnet) and Google (Gemini). So I login to see what's going on and what can be done. I talk with ChatGPT a bit on the side to help me craft the perfect prompt. Then I feed that into Lovable to see what the result is. My intention is to have it build the scaffolding and beginning of the front-end so I can continue developing the back-end and have the app up in a weekend. This should go like a breeze, right? Wrong... Problems Current AI Limitations Perception Created Results of Perception Let's break down all these points I see and the outcomes they may produce down the line in the hopes I can save at lea...

Supabase Is Not Working for Me

Image
After giving it a good trial, Supabase is just not working for me. I really did put in some effort to learn how this works and to try to run this stack. For a self-hosted setup, Supabase is just not for me. Here’s why: Out of the Box Docker Functionality Poorly documented issues AI Access is not built-in (as advertised) Self-Hosted != BaaS Scale? Out of the Box Docker Functionality They say it’s supposed to work out of the box … Just clone the code. Copy your project over. Run docker compose up and you’re off and running to the races! Want more customization? Configure as needed! This was not the case for me. I had to heavily mull thru the docs, configuration, learn the setup. Then on top of that, I HAD to setup my own domains (e.g. studio.mydomain.com, analytics.mydomain.com, functions.mydomain.com, et al) because it didn’t do service discovery properly. I also had to change the network type to bridged because the native network type obscurred all the services and for...

My Management Style

I thought this was a great prompt and does well to represent me in this current snapshot of me. This will help others understand me better in the near to mid-future. Prompt If you were to guess at my management style, based on what you know about me now. What would you say that style is, where are my strong points and where are my opportunities for improvement? ChatGPT-4o Based on everything you’ve shared, including how you structure your thinking, prioritize autonomy, and navigate emotional and technical systems, here’s a clear profile of your likely management style , along with strengths and areas for growth. 🧭 Your Likely Management Style 💠 Visionary Builder (with Technocratic-Purple Leanings) You’re someone who: Builds from first principles , not just trends Sees the big picture long before others do Thrives on autonomy , mastery, and meaning Wants others to grow through trust, not control Balances logic with deep emotional awareness You're not the kind o...

ChatGPT Codex

Regarding: ChatGPT's recent release of Codex I can see so many ways in which this can go right and wrong and in between. Ways it can go right: Vibe Coding : Developers are starting to learn how to incorporate and use LLM's with coding software. This whole "vibe coding" movement is another tool, not a replacement to writing code. There are far too many edge cases and problems with Vibe Coding that warrants a skilled developer to be able to troubleshoot issues and offer a creative hand where LLM's cannot provide. Developer Workflow : I've seen where folks are starting to learn how to spoon feed the LLM a prompt about a specific context, let it work on that context, review the changes, then work on the next context as completion runs along. This isn't new. I've seen devs plan out their functions before filling the body of them with the operations they should consume. This results in more efficient development and hence the reason why TDD ( Test Drive...