My attempts at making AI produce less slop and technical debt when helping with code generation.
All tagged code
My attempts at making AI produce less slop and technical debt when helping with code generation.
You have a running joke with friends and you’re a nerd, so you buy a domain involving the joke. Hilarious. But what if you decide to actually use it for something halfway useful?
Since I now am using one brand of inverters instead of two for my solar panels, I can now monitor things down to the individual panel. With limits…
I wrote the ultimate encryption implementation, wow it is so good! However as far as usability for the average person (or even ultra nerd) leaves a lot to be desired. A WHOLE lot.
I wanted to use AI but in a way that was responsible, didn’t dig into my privacy, and helped me to get what I want. One might say I am “hacking” AI. Maybe I am. I’m trying to get it to do what I want it to do on my own terms - the essence of hacking. But first, I had to devise a test. Granted, this test is for my needs, but maybe you might find it interesting as well.
I’ve noticed ports scans. A lot of them. However these are different, these are all scans from a seemingly distributed scanning network spread out over multiple IP addresses.
I did a bit of an experiment with several LLMs and code generation, and one of them actually seemed to perform slightly better from a security perspective.
Things have been a bit quiet lately on the blog front, in spite of me being quite busy. Here’s an update.