Update: 20260315 - Another proof of concept in the wild.
It seems like everybody else is either saying that LLM technology is either true artificial intelligence and we should all bow down to it (it is not, and fuck that noise) and we'd best get used to it, or that it's going to destroy everything and we'd best get used to it (it's not but some mornings it feels that way). Plenty of people with more going on than I do have litigated this to hell and back, marketing companies are doing marketing company things, and frankly I don't care to …
It's been another one of those months, where just enough is going on that it's hard to keep track of what, actually, is going on, but not so much that it's impossible to put together and write about. Yet, weirdly it's ideal for lots of shower thoughts that, individually, don't add up to a whole lot. It's the exact opposite of a sweet spot for somebody with ADD. So I'm more or less forcing myself to sit down and write this to keep values in those registers. It's undoubtedly going to suck but I figure I have enough editing time …
sharkfinning - verb, gerund - Learning something from scratch in an entirely hands-on way, which is to say, "Swimming with the sharks." When you don't know what you're doing or how to do it, but you have a job to do.
As the title of this post implies, I've been working on some stuff lately that's been taking up enough compute cycles that I haven't been around to post much. Some of this is due to work, because we're getting into the really busy time of year and when I haven't been at work I've been relaxing. Some of this is due to yet another run of dental work that, while it hasn't really been worth writing about has resulted in my going to bed and sleeping straight through until the next day. And some of it's due to my hacking …
debuggery - noun - The unshakable feeling that your code is completely fucked when you spend multiple all nighters in a row tracking down a single annoying bug that winds up not being in your core code, nor any modules you've written, nor any of the libraries you're using, but in a different part of the system entirely. In other words, your code is so poorly architected that you can't tell when problems aren't actually in your code.
In the last post in this series I talked about the origins of my exocortex and a few of the things I do with it. In this post I'm going to dive a little deeper into what my exocortex does for me and how it's laid out.
My agent networks ("scenarios" in the terminology of Huginn) are collections of specialized agents which each carry out one function (like requesting a web page or logging into an XMPP server to send a message). Those agents communicate by sending events to one another; those events take the form of structured, packaged pieces …
So, after going on for a good while about software agents you're probably wondering why I have such an interest in them. I started experimenting with my own software agents in the fall of 1996 when I first started undergrad. When I went away to college I finally had an actual network connection for the first time in my life (where I grew up the only access I had was through dialup) and I wanted to abuse it. Not in the way that the rest of my classmates were but to do things I actually had an interest in. So …
I was unfortunately ill-prepared for the interview because I ran home from work and jacked in without taking the time to get my head or my notes together, so I made quite a few gaffs. I hate it when I'm operating half in work …
