Something a little different for this week’s recap. I’ve been thinking a lot lately about the practice of data science education in this era of widely available (and really good!) LLMs for code. Commentary at the top based on my own data science teaching experience, with a deep dive into a few recent papers below.
The majority of developers use LLMs to help write code, present company included. When I’m working in languages I know well, they're fantastic at handling the grunt work: generating boilerplate, suggesting completions, and writing tedious tests and documentation.
OpenAI introduced the ability to create custom GPTs back in November 2023. I wanted to try to create one of these, and in the spirit of learning in public this post describes how I made it. But first, what does it do?Gene Info Custom GPT Gene Info custom GPT The Gene Info custom GPT takes a list of human gene symbols as input.
Background Bluesky, atrrr, local LLMs I’ve written a few posts lately about Bluesky — first, Bluesky for Science, about Bluesky as a home for Science Twitter expats after the mass eXodus, another on using the atrrr package to expand your Bluesky network. I’ve also spent some time looking at R packages to provide an interface to Ollama.
I had good intentions to give NaNoWriMo a try this year but didn’t get very far. Instead I gave OpenAI’s Creative Writing Coach GPT a try for a (very) short story I had in mind, inspired by my frustration trying to access closed-access research articles for a review article I’m preparing.
A few days ago I wrote about translating R package help documentation using a local LLM (e.g. llama3.x)… …when Mick Watson commented: I was already thinking of wiring up something like this using local AI models — something to summarize podcasts, conference recordings, etc. The relatively new (as of this writing) Gemini 2.0 Flash model will do this for you for YouTube videos. But what if you wanted to do this offline using a local LLM?
Last week I posted about a web app that turns a GitHub repo into a single text file for LLM-friendly input. This is great for capturing LLM-friendly text from a GitHub repo, but what about any other arbitrary website or PDF? I was catching up on Simon Willison’s newsletter reading about an app he made with Claude artifacts that uses the Jina Reader API to generate Markdown from a website. You don’t need to use the API to do this.
Using LLMs in R Most of the developer tooling for AI/LLM training and evaluation is Python-centric, but just over the past few months we’ve seen a surge of new tooling for AI/LLM applications for the R ecosystem. ollamar and rollama provide wrappers around the Ollama API allowing you to run LLMs locally on your machine.
If you use ChatGPT, Claude, or even some local model through Ollama or HuggingFace Assistants, you’ll know that the chat interface makes it challenging to feed in an entire repo like a Python or R package, because functions, tests, etc. can be scattered across many files throughout a repo.
I am in the middle of writing a review / perspectives paper. One that I’m confident will be exciting once we get it published. Some sections of the review cover subject matter at the outer periphery of my expertise.