The LFS users are still busy growing their coffee plant
In a similar spirit I have written a tiny R package that renders your plots to look like they were printed on your reviewers shoddy printer.
NCD would probably be delighted to have something that can be turned into multiple rods from god
The carton is nice an all. But imagine taping an ublock origin poster over all of these ads.
Machine Learning enthusiasts: Why settle for linear regression when you can deploy a Gradient-Boosted Random Deep Neural Net Surface Vector Cluster that consumes the entire power of Iceland to trace a perfect ∞-dimensional hypersphere around those blue points? Overparameterization is the future!
tidyllm: Integrating Large Language Models into R
Hey lemmy rstats, I’m excited to share tidyllm, an R package I wrote that makes it easy to work with large language models like ChatGPT, Claude or local models via ollama directly in your R workflow. Use it for tasks like document summarization, text classification, or structured data extraction with built-in support for JSON, PDF processing, and multimodal models. Check out its package page or the the two use-case articles on the tidyllm website about classifying text or question answering with pdf dcouments.
Lionel Hutz best joke
cross-posted from: https://lemmy.world/post/21044008
> oops, shouldn't have this bar association logo here either. munch munch
Oh, Sisco does war crimes too!
This is absolutely brilliant. Why does this not exist yet?
Needs a special kind of Captain to commit a war crime due to a traffic conflict.
A GPT-4 level language model and current Flux dev can easily run on a standard M3 MacBook Air via ggml.