Dewwy's Blog

LLM tools have become very rapidly widely talked about among all people involved in software. In amongst this there is a lot of fear. LLMs have reached the tipping point on the automation curve where they're both cheap and good enough that avoiding them all together just doesn't make practical sense.

Understandably, many people are worried that their skills are soon to be useless and they might be better off going into a different career sooner than later. I won't deny that this might happen. The machines may outstrip us in intellectual and creative capacity. But if this happens your problems —and society's— will be so bizzare relative to all previous human affairs that it's hard to say what you should do to be best placed afterwards. So instead I'm going to focus on what to do before that, while current trends continue, by talking about previous instances of automation.

When power looms were invented the quality of the fabric they produced was to put it mildly, shit. Power loom fabric was thinner, stiffer, less durable, and had a limited range of design complexity of patterns it could accomodate. The work of handloom weavers continued to be softer, more plush, more durable, and accomodate extremely complex design patterns. It continued to be this way for a long time. In some respect, forever actually. Handmade clothes still bear the reputation of being more durable, more comfortable and so on, and they have that reputation rightly. So why did the power loom win ?

In my previous post I talked about the potential to automate the data management and some rote tasks that a referee of a game of Cataphract necessarily has to go through. I have seen several different attempts at automating parts of this in different ways. Almost all involve a discord bot that reports data to discord channels from a Google Sheet. This covers some of the reporting requirements very well, but leaves something to be desired in terms of data organisation. If you want to edit the data, you have to wade through your folders of google sheets.

To solve the visual/spatial information portion of the problem (keeping track of entities on a map, moving entities around on the map, sending slices of the map to player commanders as scouting reports) the most powerful solution I have seen so far involves scripting on top of Foundry.