Nevertheless, referencing the LFR work and merely including a link where the paper is discussed feels a little like beating around the bush. The primary article doesn’t seem to use the words “self-similar” nor “fractal” - if you’re only interested in LFR work, why reference Mandelbrot at all?

https://www.researchgate.net/profile/Ion-Andronache/post/Wha...

Additionally, I also thought it was customary to store a pointer to the source in the same row as the vector (i.e. vector+ doc path + page#/paragraph/etc.) OR just store the original text chunk (though based on your disk reqs doesn’t sound like it would have been feasible).

Glad you’re having good results! Maybe you’ve inspired me to finally try out a similar setup myself!

At least when I report fraud to credit card or my bank, they can stop or undo/chargeback a transaction.

> clean, concise, single button

> uvex add other_slop_project —-disable_peddled_package_recommendations

> implicitly phoning home your project, all source code, its metadata, and inferring whether your idea/use-case is worth steamrolling with their own version.

This is the future of “development”. Congrats to the team.

> "...a mathematical transformation, sort of like the Fourier transform. It encrypts data using a quantum-computer-proof algorithm..."

I am assuming there is some deep learning at play here i.e. it is manipulating the data within the latent space. If this is true, then would the embedding process really be considered "encryption"? You could argue it is security through obscurity (in the sense that the latent space basis is arbitrary/learned), but it feels like two different things to me.

More recently though, I must say, YouTube has really jumped the shark in terms of perfecting their dark patterns/algo stickiness. I can’t even go to the site without immediately forgetting my original intent.

The problem is two-fold… abstract thinking begets more abstract thinking, and the common advice to young, aspiring entrepreneurs of “scratch your own itch” ie dogfooding has gone wrong in a big way.

> TLDR This should be at the start?

I actually have been thinking of trying out ClaudeCode/OpenCode over this past week… can anyone provide experience, tips, tricks, ref docs?

My normal workflow is using Free-tier ChatGPT to help me interrogate or plan my solution/ approach or to understand some docs/syntax/best practice of which I’m not familiar. then doing the implementation myself.

> “this is the future of culture”.

The point is that the future of “culture” is increasingly decentralized; that the ability or more aptly, the opportunity, to accumulate “cultural influence” will tend towards higher entropy as a direct repercussion to the proliferation of the means to accumulate it.

Put differently, as the hardware and software used to record, store, and share content become more widely accessible, anyone with the access and motivation to use the tools truly has the opportunity to become famous.