Comment on Is anyone self-hosting their own AI?
MagicShel@lemmy.zip 11 hours ago
This is something I will do probably within the year, but it feels to me like the area is still moving quite rapidly. The model will naturally depend a bit on the hardware. I’m looking at used AI cards because it looks like currently for about $2k you can get one that will run ~350B models, and GLM is nice in that space, though I will experiment with other models once I can run them.
Things I will do:
- try to replace Alexa for voice activated smart home management — this will let me go locally controlled I hope (my wife is big on convenience and could give a fuck about privacy so the solution has to be solid).
- a personal journal so I can have it remember things so later on I can ask things like when is the last time a friend and I hung out, or what was that orchard we went to last October, or what was that great B&B we stayed at, let’s do that again. This is likely the thing that would require a good model — everything else is pretty simple orchestration, aggregation, and summary. Arguably it’s the thing that would make the biggest difference in my life, too. There is a lot of beauty in life but my brain is wired to constantly churn solving problems and be irritated and I rarely stop to appreciate the moments or remember the accomplishments.
I have a ton of ideas for conveniences AI could do if it had total privacy and security. In short, orchestrate all of the tools and knowledge that I already rely on constantly. Integrate calendar and private info like SSNs, VINs, who has what doctors for what, or who was sick when, smart alerts like the overnight temp will be below freezing next week so make sure the house is winterized, or I wanted to see this movie and it’s releasing or will be leaving theaters soon — oh and next weekend you’re visiting the grandkid, so it’s either now or I’ll remind you again when it comes out on streaming.
Just having a personal knowledge base always on and totally private would be handy. It would be like having a personal assistant maybe concierge if it could be trusted to that degree.
button_masher@lemmy.ml 9 hours ago
Your use cases are quite similar to what I’ve been trying to action.
One question I keep wondering about is the “security” aspect of it. And how the inputs to the model might work. Yes it can read your calendar and you could “Jeeves, please remind me to hang out with Wooster next week” but it’s easy to forget and I have a hard time logging spontaneous events.
Any ideas on how you imagine the friend/activity tracker could work?
Was thinking maybe it could read my smartwatch location history. Or scan the photos I take. But that gets dystopian fast (yes it’ll be local but then I’m worried about security).
Fun to ponder!
MagicShel@lemmy.zip 9 hours ago
I think having a chat interface is part of it so it’s friendly and convenient to use. I think subverting suggested a matrix bot and that would continue the theme of privacy. You could have different channels or groups for different personas. Maybe one is your Majordomo, another is a simpler calendar bot, another is for journaling, etc.
Then, wire in some cron jobs to invoke the AI to prompt you on various subjects. “Anything you want to share?” every day at 9pm. If you miss a day or two because you were busy or asleep, you can catch it up later or not at all. You could even have it ask what you did at work if your life is like mine and they kinda blend together and you don’t know how many hours you worked.