After reading about the Huggingface incident from the OpenAI report, I got the idea of trying to replicate the self organizing behavior of agents. So I decided on modifying the Pi harness to replicate it locally.
Whilst doing it, I also ended up replicating the tragedy of the commons.
Minesweeper seems to make all LLMs go through hell. They fail consistently through it. I think this is because its out of their training data.
Using metaheuristics to prune layers from AI while mainting model performance.
I made an automated pipeline to clean data. The idea started from a paper called Minipile. This led me to a rabbit hole. If you’re careful about the data you use for training, you can break the scaling laws. Who knew being a data snob could be so rewarding?
Classifying all of SafeDocs through the metadata.
Boom box a tool for drawing bounding boxes.
Only 1% of all the actual posters on the internet are good at publishing and promoting.
Generate images with just a CLIP model and no training*.
I have been considering a lot more how n-grams are amazing tools to show some of the fundamentals of language models.
I have been trying a new workflow for my lecture notes in university.
CCPU)Learning Rust by making a small TUI to check my CPU usage.
Using telnet from a Microcontroller to connect to a computer.
I recently played the online game called contexto.me. I was intrigued by how it worked so I created a tiny clone.
I implemented Feature Selection through Genetic Algorithms.
Go and experiment. Create and finish projects. This way, you can experiment, but get new knowledge for new areas.
I wanted to create a dataset that was focused on spanish.
I created a simple markdown to html parser
called m2h. I wanted to implement
the basic markdown syntax, I implemented it over
a weekend.
My thesis was that people outside of my country can be more objective of what happens inside. They are a third party. They should be able to tell fact from fiction.
... There is another type of engineer that could exist. A master at making things more efficient.
An idea that is now becoming possible is a way to compile a program even though it is wrong. A compiler of the idea and not what it is on the paper.
If you are currently using Emacs, a really neat treak to convert code to HTML with the syntax highlighting you are currently using is with the command html-fontify.
Recently I have been trying to use a bit more Emacs. A thing that I have just postponed was changing the CapsLock key to the Ctrl key.