Freeposity
@Freeposity@lemmy.world
- Comment on Thoughts on coding with AI: my experience 2 weeks ago:
Try this out www.youtube.com/watch?v=4Hvkv_I8QDE
This is where I learned of it, but I’ve also hooked up unsloth desktop to the same obsidian knowledgebase. This way the long term memory persists across my LLM client tools. Right now I have it keep track of me and my preferences, my wife and her preferences, home lab architecture and documentation and technical project information for me and my wife.
- Comment on Thoughts on coding with AI: my experience 2 weeks ago:
Italian is a beautiful language, probably my favorite one.
As far as your post is concerned, I’m using qwen 3.8 27B as my main local LLM. I actually do have it push code to a github repo. Mainly because I have no real interest in learning the code it is writing, I’ve always been a back end and data person and I’m having it write web stuff. One thing I do a little differently is I make sure the model writes documentation up front and then at the end and also any steps it discovers, that it should remember into an MD file. This is so it doesn’t make the same mistakes over and over.
I also make sure it writes instructions for itself(or another model) and I will sometimes have another model check its work.
I have started implementing long term memory with obsidian as its “second brain”. This way I don’t have to keep explaining who I am or what we’re doing, what machines are available, what my preferences are, etc…
I think in a few weeks I’ll be able to grab my phone and start giving it tasks to do, using Hermes.
Nice write up. I appreciate you taking the time to share.
- Comment on Thoughts on coding with AI: my experience 2 weeks ago:
It’s clearly written by someone who is not a native English speaker. I noticed that in the first paragraph or so.
Or do you think an LLM would write “…i can finally say i am quite satisfacted”
This is not to crap on OP, I’m very impressed with their command of English.
- Comment on Self-Hosting Survey 2026: What are your favorite self-hosted apps? 1 month ago:
Oh yeah, I’ve got a box of esp32s and mmwave sensors waiting for me to get my soldering iron out. I’m with you, they’re great. I suppose I could somehow figure out out how to do SDR with an ESP32, but I’ve got plenty of unfinished projects waiting for me as it is. ESPHOME makes edge devices so easy to create. And it gives me an excuse to do a little soldering and 3d printing.
The ESP32s are also really good for making old devices smart. One project in my queue is turning a bunch of air purifiers into smart devices that HA controls. They were super cheap and there’s nothing to them but a fan, and a filter but they’re loud. I’m going to make it so they only run when no one is in the room.
- Comment on Self-Hosting Survey 2026: What are your favorite self-hosted apps? 1 month ago:
I was thinking the same thing. My path was self hosting on old desktops for the longest time then the pi came out and I ended up doing a birdnet project, then home assistant and now I’ve got about a half dozen data collectors on pi zero 2 w machines. They are pretty much set and forget. I use an orange pi for my instance of Solar Assistant because I wanted something that was not affected by anything but the network and the inverter and I know how rock solid these little machines are.
But in the last few years I’ve started embracing docker and NUCs and have pulled apps off Synology, making it just a file server at this point.
So technically I have more raspberry pis than anything else but they are really just edge devices, except for Home Assistant. And it will probably stay that way until there is a good reason to switch. I don’t see that happening for years.
- Comment on Self-Hosting Survey 2026: What are your favorite self-hosted apps? 1 month ago:
AI Pioneer 🤖
- Fleet: 6–10 devices · 21–50 TB
- Motivation: Privacy & data ownership, Independence from Big Tech & subscriptions, Learning & experimenting
- My MVPs: Portainer, Open WebUI, Ollama, Nginx Proxy Manager, arr stack