The Wednesday Wellness threads are meant to encourage users to ask for and provide advice and motivation to improve their lives. It isn't intended as a 'containment thread' and any content which could go here could instead be posted in its own thread. You could post:
-
Requests for advice and / or encouragement. On basically any topic and for any scale of problem.
-
Updates to let us know how you are doing. This provides valuable feedback on past advice / encouragement and will hopefully make people feel a little more motivated to follow through. If you want to be reminded to post your update, see the post titled 'update reminders', below.
-
Advice. This can be in response to a request for advice or just something that you think could be generally useful for many people here.
-
Encouragement. Probably best directed at specific users, but if you feel like just encouraging people in general I don't think anyone is going to object. I don't think I really need to say this, but just to be clear; encouragement should have a generally positive tone and not shame people (if people feel that shame might be an effective tool for motivating people, please discuss this so we can form a group consensus on how to use it rather than just trying it).
Jump in the discussion.
No email address required.
Notes -
Offline ai models make weird mistakes even when they're 30b in size. Mine kept looping uselessly when I asked it to make some statistics on a pretty simple log file.
Yeah, I expect that pretty much comes with the territory, but I've got it up and running and I'm still interested in kicking the tires and playing around a bit!
Do you think there are any special tricks to getting a relatively small (offline) model performing well? I'm thinking that maybe it's extra necessary to be really clear in ones prompting.
I think it's certainly possible, and I can't help but believe that llm-fu is a Thing just as Google-fu is a Thing, but I'm too new to the llm scene to be able to currently have a decent idea one way or another with any real authority. I've got several different models that I want to test out for different things, but the two big things I want to play around with are training an llm with custom data, and automating a bunch of my wife's standard tedious tasks, like writing progress notes (which I'd like to sound like her thanks to said custom data training, if possible), entering visits into the software her biller is using, and sending out appointment reminders. Not to get too far ahead of myself, but if an offline model is up to that task, then I might pursue setting up an Openclaw agent for her to use for extra lulz, but all of this is just window dressing on the underlying desire to tinker, which is a desire that I want to feed now that it's back after fading in the teens and being completely absent for most of this decade.
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link
More options
Context Copy link