Several recommendations for LLM usage in the context of open source.

“The long term goal of software freedom is to eliminate the harm of proprietary technology. While we work toward that greater goal, we should seek to mitigate the harms that we cannot immediately eliminate. These recommendations aim to abate the damage of these systems, and also consider how these tools might counter-intuitively help us advance FOSS.”

Detailed, nuanced, and well-thought-out. Tons of great and insightful quotes from RC alums. And their conclusion is, I think, perfect:

You should use AI-powered tools to complement or increase your agency, not replace it.

I really like trying to publish written versions of conference talks – videos are great, but not everyone has the time or desire to watch. But in the past I’ve often not been able to make them happen – it’s just felt like a lot of work transcribing an entire talk, producing a writeup, etc. But modern AI tools have changed this, it’s now significantly easier.

So here are some notes on my tools and workflow that I used to produce the writeup of my DjangoCon US 2024 talk. This is super-similar to, and inspired by, Simon Willison’s workflow.

Maybe the best intro to LLMs I’ve seen yet.