[tif] semhash for semantic deduplication
I often find myself in a position where I have to deduplicate. And most of the time, it’s a lot of data that needs to be deduplicated. So I keep my eye out f...
Recent Posts
[til] cloud gpus with the prime intellect cli
Today I spun up a pair of A100 80GB gpus for $3.25 / hour using the prime-intellect-cli. I wrote briefly about prime intellect earlier and had spun up some G...
started building a large language model cli
I wanted to learn a little more about uv (Python project and package manager) and I wanted to experiment with a command line interface for large language mod...
[tif] andrew white from futurehouse on automating scientific discovery
Andrew White head of science and co-founder at FutureHouse on Nathan Labenz podcast The Cognitive Revolution posted 2024-12-05.
[tif] prime intellect working on compute, research, intelligence
Prime Intellect founded by Vincent Weisser and Johannes Hagemann
[tif] simon willison on link blogs
Simon Willison is a co-creator of Django, gives great talks at events like PyCon, and is the kind of netizen we should all aspire to be more like. In hi...
[til] setting up jekyll site deployed to github pages
This is how I setup a static Jekyll site hosted with github pages. The code is hosted at https://github.com/galtay/blog and the site is hosted at https://gal...
[tif] sam rodriques from future house on natural language in bio foundation models
Sam Rodriques Director and CEO of FutureHouse, a non-profit working on AI agents to automate research in biology and other complex sciences, discusses the n...
[til] changing default ollama storage location on linux
I was downloading some large ollama models and ran out of space on my linux machine. I then realized that the default model storage location is /usr/share. T...