My De-Claudifying Memory File to Ditch Claude's "Word Mosaics"
How I at least partially mitigate Claude Fable's ridiculous yoda-speak
The End(s) of Argument
Looking for the structure underneath the noise
Live Last read · last published · next check
Latest posts
Blog Posts as LLM Repair Code
To Fix the Crappy Prompts Claude Wrote for You, Have Claude Read My Blog Post
I Finally Understand Why LLMs Suck at Writing Prompts (And It Might Be Fixable)
I've wondered a long time why LLMs are so bad at writing prompts for users to use when they seem to be so good at prompting on the fly. It turns out the two things are related.
Four Tips for Better Prompting
A generalizable and durable approach to investigating an issue with an LLM.
Tagging Motel Noir
An example of how LLM projects find depth, and how people find curiosity
We could be building a better world with our students. Why are we disempowering them instead?
And why did our constructionism impulse die when it was most needed?
A simple starter film data prompt: Calculating on-screen film deaths in 1998
A simple prompt to understand some basic LLMs + data + interface concepts
Tilling the Garden: A different way to use AI to make interesting and useful apps
Rebuilding the internet of weird little things one data enrichment at a time
Introducing Plotwise, the slightly weird film explorer
Running a recommendation engine off of HTML and 5 MB of JSON
An interesting attribute tagging approach with LLMs
And why the literature on cognitive surrender can feel a million miles away to people who use this stuff