Anatoly Tsyplenkov

I have recently been enjoying using Gemini 2.5 Pro in Google AI Studio instead of Stack Exchange :omya_google: . The large context window (1M tokens) and the ability to set the temperature to 0, meaning NO CREATIVITY, make this LLM a very good tool for RAG when communicating with your own materials. For example, I recently had a small question about the applicability of a ridge regression model that I trained in #RStats using the #tidymodels framework some years ago.

@josi Appreciate your comments. This is all thanks to you and your posts. You made me lean towards rust. Now I am an #rstats enthusiast by day and a #rustacean by night.

Just learnt about the #quadbin spatial indexing. There is not much information about it compared to #geohash, #h3 or #s2. Has anyone worked with it before? Are there any pitfalls that I am missing, because it sounds freakin cool.

Just wrote a small #weekendcoding project — `pastum` VS Code/Positron extension that mimics the legendary `datapasta`📦. Copy any text table and paste it in the editor as a dataframe object of your favorite framework/language #Python #RStats.

It ships with recognition of float, integer, and strings types. So even @datapolars won't complain that you forgot to put `.0` at the end of your numeric value! Heavily inspired by latest @coatless developments 🙏

https://open-vsx.org/extension/atsyplenkov/pastum