Garage Intelligence

If I currently ask my current A.I guru (Perplexity) whether this is a good idea or not, it'd probably suggest turning off the computer, stepping outside and immersing my fingers into the nearest patch of grass. Even LM Studio itself has said 'You know what, this is probably too big to take on you know.' But what could possibly go wrong with using an oversized model that's probably going to take an hour between answers here if it actually does come up with some decent well thought out answers? It's not like I can't wander off, cook some food and come back after eating to learn what it thinks. So welcome to my first trial with the beast that is QwQ. Shhhh, don't startle him!

It's all well and good saying things along the lines of 'The way A.I is going, it's going to take over the work soon enough!' but while that might be the case if someone accidentally gives Grok nuclear weapons codes, it certainly won't be through anything I'm trying on for size at the moment.  This week I looked at using a local A.I build on my computer and a couple of A.I models to make me rich and neither of them really got off the ground or make me a single cent ultimately. So it looks like I'm sticking to my day job (and any revenue through blogging obviously) for now. But in case you're wondering what didn't work here, allow me to elaborate. 

Sigh, all I wanted to do this morning was a little 3d printing. Instead I found myself dealing with a overzealous Windows bouncer and a keyboard that's suddenly started hallucinating badly.