> Is anyone making LLM-in-a-box for emergency supply kits yet?
Maybe someone should be making this, but for rebuilding society in the event of a disaster - a solar-powered black box with most of humanity's knowledge within. Even something running one of the Qwen models would be useful.
"So, we had a nuclear war and need to start from scratch. How do I turn this rock into a computer chip?"
Anecdotal, but I'm convinced it screws up sleep quality. I'd just accepted for the longest time that waking up groggy with a slight headache and tired was the norm until I put a CO2 monitor in my room. With the door closed, it climbed up to 1500ppm in under an hour.
I'm certain many people are sleeping in similar conditions without realising and ventilating their rooms properly or leaving the door open.
Ticks in my part of the world were never such a large problem. It was rare that you'd get one on your leg in the field behind our house, and now, you literally can't walk through the grass each year without having 10+ on your legs in a matter of minutes. Warmer and wetter weather and fewer hard winters. The presence of Lyme disease has also increased in them.
I have direct experience of this, so downvote all you want, climate change deniers.
Another worrying proxy for how deeply climate change is bleeding into everyday life: coffee prices, orange juice prices, and now having to engineer huge trail areas with woodchips just so people can avoid being bitten by exploding tick populations.
> 10 year old dual Xeon server...On 10 year old hardware.
Hold on, what are the specs of your rig? How much RAM?
I've been considering getting an old refurbished 2018 Mac Mini with 64Gb of DDR4 RAM but everything I've read suggests this will be way slower than my 16Gb M1 Pro Macbook.
I cannot wait until a time in the future when we have local models that are Opus 4.6+ level, and capable of running on inexpensive hardware like a 16Gb Mac. Hopefully that's only a few years away.
> I think you need to ask what you actually want to do with the AI.
What about improving the efficiency of token consumption, etc., basically opportunities for improving cost/performance?
I keep thinking there has to be a better way to share context with models than dumping entire gigantic skill files of raw text or otherwise into them - I'm betting there's a bunch of low-hanging fruit there.
Well, people keep throwing money at them, including you and investors. So why would they care? It hasn't annoyed you or a large enough portion of users enough to move off their service - because there isn't a better alternative.
I'm no fan of AI companies, but I fail to see how people using it to build open-source software is a bad thing.