Viewing profile — anon1253

Slightly off-topic but related: currently I'm in a research environment (biomedicine) where a lot of AI is used. Sometimes well, often poorly. So as an exercise I drafted some rule…

It always fascinated me how a lot of "state" in our neural networks is probably encoded in the extracellular fluids rather than in the neurons themselves. Biological neural network…

It's a fascinating topic. I've often been surprised by its use of "tapestry" (as in "the tapestry of existence") and I never really figured out why it seems to gravitate towards su…

RDF and semantic web used to be my goto's for this, as I believe many of the core ideas are still valid and often overlooked and sometimes even poorly re-implemented. Which says so…

Code is up https://github.com/vortext/esther but it's still heavily work in progress :-)

https://github.com/vortext/esther Esther is my personal project to develop a diary app that talks back. Basically. Along the way I learned how to htmx, llama.cpp via JNA and practi…

Cool! And on top of that TheBloke has the quantized models of course: https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF …

Probably soon! I'll post it here. Still finalizing some Retrieval Augmented Generation things. It's written in Clojure with a very thin HTMX front-end. However there are some inter…

I typically write them myself in the form of a "you are-such-and-so, your role is this-and-that. As such-and-so you have the following traits..." and so on. Sometimes I let some ot…

I'll give those a shot as well, thanks! It's a tricky balance sometimes between "I should actually finish building the thing I am trying to build" and "ooooh shiny new model to try…

Being one of those people that still recommends Emacs and have sunk countless hours in my personal dotfiles: I kinda enjoy doing it, that's why I am doing it. It feels great having…