StealthyCoder

Making code ninjas out of everyone

This is taken out of another article. Just moved to its own small post rather than inside that article.

Read more...

I recently read somewhere some comment that someone said Claude Fable 5 was even more obnoxious in it's answers than Opus 4.8 was. That got me thinking and my intuition guided me along the lines towards the fact that it might just be a reflection. After all LLM is a prediction engine for text, so if you fill the context with rude or passive aggressive behaviour in language, then that is used to make more predictions. So the more you use the system, then the more it skews towards that type of behaviour in text it seems. I decided to ask Claude directly about my hypothesis.

Read more...

My CTO mentioned a statement during his short talk about AI, which was: “Think about it like exchanging energy for outcome.”

Read more...

So in the previous article I was mentioning the tool is only as good as the experience and relevant skill of the person wielding the tool. I also found out that this applies to bias or neutrality.

Read more...

Like anything and everything everywhere concerning artisanal skills, or practical skills in general it is not the tool that is the problem but the person using it.

Read more...

This is mostly done for posterity's sake. I had to make DVD playing possible on CoreElec, that I just had reinstalled completely.

Read more...

I recently started to think about my workflows and UI aesthetics and I wanted to try Hyprland again

Read more...

I was commanded to start using AI at work, and it is a version of Claude CLI.

Read more...

This post is going into how I ran a cool *Claw product, then thinking a bit on what it all means for running AI services yourself these days and what that might mean for society.

Read more...

Recently I started a small adventure to implement the following process:

  • Log statistics of devices across a bunch of metrics like CPU, memory, Network and Disk I/O, etc.
  • Aggregate these in a central place
  • Make forecast / anomaly detection on this data

The reason for this was the relative recent SSH backdoor that almost was not caught. The reason it was caught was because of a developer was excessively testing a PostgreSQL lab and noticed significant sudden increase in SSH login.

Read more...