§1 Find My Cite
I had made a resolution to myself that I wasn’t going to play around with any of the many LLM (Large Language Model) tools that have popped up as of late, but I might reconsider after reading this pitch:
Are you a Zotero user? Do you ever wish you could search your libraries by ideas—not keywords? Then this page is for you. Follow the steps below to download information from one of your group libraries and search it using an “idea” search. That is, it will match your search with the semantic content of text from your library. That means you don’t have to use the exact language found in a text to find a cite.
This is an archival version of Find My Cite.
Before you “Use the tools here to interact with a Zotero group of your choice. You can find propositions, ask questions, or get supporting text” … make sure you read the Introduction to Find My Cite:
Algorithmic BS: Exploring Uses of Large Language Models
Algorithmic BS?
Algorithmic BS: Exploring Uses of Large Language Models
The modern authoritarian practice of “flood[ing] the zone with shit” clearly illustrates the dangers posed by bullshitters—i.e., those who produce plausible sounding speech with no regard for accuracy. Consequently, the broad-based concern expressed over the rise of algorithmic bullshit is both understandable and warranted. Large language models (LLMs), like those powering ChatGPT, which complete text by predicting subsequent words based on patterns present in their training data are, if not the embodiment of such bullshitters, tools ripe for use by such actors. They are by design fixated on producing plausible sounding text, and since they lack understanding of their output, they cannot help but be unconcerned with accuracy. Couple this with the fact that their training texts encode the biases of their authors, and one can find themselves with what some have called mansplaining as a service.
So why did the LIT Lab use an LLM to build these tools, and why bother working with a known bullshitter?
§2 Make Better Spreadsheets
While my evenings this week were spent trying to re-capture some of the joy of watching a 15 minute performance I recently saw on television, much of my days were spent looking at spreadsheets made by other people. When I tell you that many of these spreadsheets were opaque and confusing, please understand that I am not trying to throw shade at the authors. Most people don’t understand the best practices associated with making a good spreadsheet so that they can be used and re-purposed by people other than ourselves.
I looked through my collection of bookmarks for good advice for making spreadsheets and found the following:
- Releasing data or statistics in spreadsheets one-pager (and background on why this exists)
- Good enough practices in scientific computing
- Data Organization in Spreadsheets for Social Scientists – Data Carpentry
These links are here for you for when you might need them.
I don’t recommend looking at Excel on a long-weekend, unless of course, you want to play games in them.