Louis Ingenthron @LouisIngenthron@social.cleverlibre.org

@freemo I've seriously considered building a computer as a wall-art installation, all flat and composed with neat wires behind a thin layer of plexiglass...

@sos Also, if you're a developer, another things it's *great* at that you may find useful is taking loosely-formatted data and formatting it properly as e.g. a CSV so it can be imported into a system. That's pattern matching too, and it's basically effortless on your part.

@sos Go ahead and try it then. It needs to work on different websites with vastly different layouts and formats, and it needs to be able to reliably exclude pages that are not recipes (even when those pages are confusingly similar, such as lists of recipes).

I was able to build that system to work universally with a locally-trained LLM in just a couple days with over 99% accuracy (it used a web-crawler, so the input was pretty solidly random). The LLM was even able to fix measuring-unit formatting issues so ingredients could be imported uniformly into a database.

I could be wrong, but I think you'd be pretty hard-pressed to get similar results with more traditional methods in the same time frame.

@augieray And, yet, strangely, the gun laws tended to be *looser* back then. 🤔

Fwiw, I'm all for reasonable gun control, but that's not going to stop psychopaths from committing psychopathic behaviour to get their face *guaranteed* on every single national news channel in the country and discussed by millions across the planet on social media.

We're going to keep having mass shooters so long as we keep making mass shooters (in)famous.

@sos Because those are all situations in which it doesn't need to draw on outside facts, or the factual nature of the output is irrelevant.

I.e. in identifying, classifying, and condensing text: I trained an ML algorithm to look at a website's HTML and tell me if it had a meal recipe (ingredients/directions/etc) somewhere in its contents. I was able to achieve over 99% accuracy, even when pulling from vastly different websites.

That's because, at their root, these are not fact machines; they're pattern matchers. So, when you give them a pattern-matching problem like "find the recipes", they don't need to draw on the larger model training to create content; they just do the job you trained them for. The medical example is similar; it's just extending a pattern identified from real patient data to generate fake patient data.

@sos I think you're wrong there. It's great at identifying, classifying, and condensing text. It's also useful in the medical simulation world for anonymizing patient data by making pattern-based fictional amalgams. It's also a great tool for scaffolding and creating placeholder content that would otherwise take a bunch of time to develop by hand. And all that's before we get into the code-completion versions of the software or entertainment purposes.

Right now it's a fad and the square peg is getting put into a lot of round holes, but when you apply the tool to what it's good at, you get really solid results.

@augieray How old are you exactly?

@mms Try looking into development for the Game Boy Advance.

It came out later, so some of the tooling is better, but because it was portable, the performance was more comparable to older full-size consoles. And there are great emulators available for testing.

The way you write directly to screen memory and swap buffers and such is a great bridge to the older, more arcane, development.

@garyackerman "but"?

@tristansnell For what it's worth, even most of us pro-2A gun owners are opposed to laws as loose as Missouri's.

It's like the lawmakers mandating genital checks for teenagers to make sure they're not trans: nobody wants this, but dumbass politicians think we do.