Your File System Is Already A Graph Database

Historically, it made deletion rather difficult with some problematic edge-cases. You could unlink a directory and create an orphan cycle that would never be deleted. Combine that with race conditions on a multi-user systems, plus the indeterminate cost of cycle-detection, and it turns out to be a rather complex problem to solve properly, and banning hard-links is a very simple way to keep the problem tractable, and result in fast, robust and reliable filesystem operations.

This is exactly what we're working on, is there any application in particular you're interested in the most?

> I'm struggling collecting actual data I could use for fine-tuning myself,

Journalling or otherwise writing is by far the best way to do this IMO but it doesn't take very much audio to accurately do a voice-clone. The hard thing about journalling is that it can actually be really biased away from the actual "distribution" of you, whether it's more aspirational or emotional or less rigorous/precise with language.

What I'm starting to do is save as many of my prompts as possible, because I realized a lot of my professional writing was there and it was actually pretty valuable data (especially paired with outputs and knowledge of what went well and waht didn't) for finetuning on my own workloads. Secondly is assembling/curating a collection of tools and products that I can drop into each new context with LLMs and also use for finetuning them on my own needs. Unlike "knowledge repositories" these both accurately model my actual needs and work and don't require me to do really do anything unnatural.

The other thing I'm about to start doing is "natural" in a certain sense but kinda weird, basically recording myself talking to my computer (verbalizing my thoughts more so it can be embedded alongside my actions, which may be much sparser from the computer's perspective) / screen recordings of my session as I work with it. This is something I've had to look into building more specialized tools for, because it creates too much data to save all of it. But basically there are small models, transcoding libraries, and pipelines you can use for audio/temporal/visual segmentation and transcription to compress the data back down into tokens and normal-sized images.

This is basically creating a semantic search engine of yourself as you work, kinda weird, but IMO it's just much weirder that your computer can actually talk back and learn about you now. With 96GB you can definitely do it BTW. I successfully finetuned an audio workload on gemma 4 2b yesterday on a 16GB mac mini. With 96GB you could do a lot.

> letting LLMs write docs and add them to a "knowledge repository"

I think what you actually want them to do is send them to go looking for stuff for you, or actively seeking out "learning" about something like that for their own role/purposes, so they can embed the useful information and better retrieve it when they need it, or produce traces grounded in positive signals (eg having access to this piece of information or tool, or applying this technique or pattern, measurably improves performance at something in-distribution to whatever you have them working on) they can use in fine-tuning themselves.

You can fine-tune local models using your own data. Unsloth has a guide at https://unsloth.ai/docs/get-started/fine-tuning-llms-guide.

I'm currently experimenting with Tobi's QMD (https://github.com/tobi/qmd) to see how it performances with local models only on my Obsidian Vault.

Right, the technical know-how about fine-tuning isn't the problem here, getting sufficiently high quality session logs without basically giving away my private data for free is the issue.

Today, I can use even the small models of OpenAI and Anthropic to get valuable sessions, but if I wanted to actually use those for fine-tuning a local model, I'd need to actually start sending the data I want to use for fine-tuning to OpenAI and Anthropic, and considering it's private data I'm not willing to share, that's a hard-no.

So then my options are basically using stronger local models so I get valuable sessions I can use for fine-tuning a smaller model. But if those "stronger local models" actually worked in practice to give me those good sessions, then I'd just use those, but I'm unable to get anything good enough to serve as a basis for fine-tuning even from the biggest ones I can run.

Yeah, I suppose, but how do I get sufficiently high quality synthetic data without sending the original data to OpenAI/Anthropic, or by using local models when none of them seem strong enough to be able to generate that "sufficiently high quality synthetic data" in the first place?