The End(s) of Argument
Subscribe
Sign in
Home
Archive
About
AI can walk through all the doors at once
An explanation of why AI can be helpful with sourcing and contextualization and why it sometimes doesn't look that way in retrospect
Sep 23
•
Mike Caulfield
9
1
Latest
Top
Discussions
My Surprisingly Effective Follow-Ups File
I've been holding back on sharing this until I could present this more fully, but let's YOLO it.
Sep 19
•
Mike Caulfield
18
8
I Am Once Again Asking You To Use A Balanced, Evidence-Focused Follow-Up
Cutting through Russian disinformation with thirteen extra words
Sep 17
•
Mike Caulfield
12
LLMs Often Conflate Images In Bizarre Ways. Here's How to Work Around It.
A short demonstration
Sep 15
•
Mike Caulfield
7
6
Do students need to know how LLMs work, or to predict how they'll act?
A little venting about what educational explanations are for...
Sep 12
•
Mike Caulfield
17
9
Is "Are you sure?" a bad follow-up prompt?
A very minimal test with some fairly clear results. (The answer is yes, it's bad)
Sep 9
•
Mike Caulfield
9
Does successful LLM iteration require previous knowledge of the right answer?
Answer: No.
Sep 7
•
Mike Caulfield
14
6
Is the LLM response wrong, or have you just failed to iterate it?
Many "errors" in search-assisted LLMs are not errors at all, but the result of an investigation aborted too soon. Here's how to up your LLM-based…
Sep 7
•
Mike Caulfield
38
22
See all
Recommendations
View all 9
Nate’s Substack
Nate
The Weird Turn Pro
Andy Masley
AI-Learn Insights
Alfred Essa
Aaron Tay's Musings about Librarianship
Aaron Tay
Simon Willison’s Newsletter
Simon Willison
The End(s) of Argument
About
Archive
Recommendations
Sitemap
