Hello!

The last time I wrote was 2019. This is ages ago! So many have many things have changed. Most notably, in our line of work, the advent of AI. Or more specifically, the rise of the Large Language Models.

And yes, I am a power user. I use Claude Max, Claude Code, Github Copilot Enterprise and occasionaly Perplexity and ChatGPT. Lately I also dabble with Microsoft Scout and M365 Copilot.

I have created my own agents and skills and can now delegate a great part of my work (consultancy, coding and platform engineering) to a model.

However, I see the dark side too. My work is done faster, but my brains are getting tired and less happy. So that is why I started to write this blog post myself. No AI here, pure me.

Also, I see the dangers of (over)sharing with large language models. We share way more with these, then we do via Social Media platforms or via Google in the olden days.

You share your prompts in clear text, and even though the commercial AI providers say they will not train on your text, they still have your prompts, documents, pictures, the full context processed in their GPU's caches. Not sure what they do with that info.. but believe you me this data is gold for them.

That is why I bought a MacBook M4 Pro Max a while back.. with 64 GB of RAM so I can run these models myself. Even when airgapped. And I think.. everyone should.

To help you decide if you should and when you should, I created this flow chart:

Think it is pretty self explanatory.

Next time will be a more technical post about which local model to choose, how to run and what to tweak.

See you then!