this is the way LLMs _should_ be used, as an assistant to create reliable, deterministic code. and honestly, they're fantastic when used this way. build the thing you need with the LLM, then put the LLM away. but in…
I uh might be skewing that as I generally just use a lot of curse words with Claude by default
I've had to migrate to mostly Python for my work, and this is the thing I miss the absolute most from R (and how it works so seamlessly with the tidyverse)
I love the story of the Framingham Heart Study, it's one I've referenced a lot when I talk to people and organizations about how they might not have the data they need and how important data collection is.
renv and rocker have really addressed these issues for using R in production https://rstudio.github.io/renv/index.html https://rocker-project.org/images/
this is the way LLMs _should_ be used, as an assistant to create reliable, deterministic code. and honestly, they're fantastic when used this way. build the thing you need with the LLM, then put the LLM away. but in…
I uh might be skewing that as I generally just use a lot of curse words with Claude by default
I've had to migrate to mostly Python for my work, and this is the thing I miss the absolute most from R (and how it works so seamlessly with the tidyverse)
I love the story of the Framingham Heart Study, it's one I've referenced a lot when I talk to people and organizations about how they might not have the data they need and how important data collection is.
renv and rocker have really addressed these issues for using R in production https://rstudio.github.io/renv/index.html https://rocker-project.org/images/