Experiments experiments
Beyond the Chat Box
A curated reader on alternative interface metaphors for LLMs, structured by metaphor family and prepared as keynote sparring material for linguists and HCI researchers.
Experiments
Hands-on explorations you can try yourself.
experiments
Hallucinated library entry: post-mortem and safeguard
How Claude invented a book by my competitor, why it happened, and the rule added to prevent it.
experiments
Book recommender: library integration
Design for integrating the book recommender with the garden library, making it the single source of truth for all book data.
experiments
Book recommender: library audit
Audit of 40 unread and in-progress books with status labels, reading patterns, and calibration data for the recommender.
experiments
Book recommender: scoring algorithm
Design for the logic-based scoring algorithm that powers the book recommender. Five dimensions, no AI.
experiments
Book recommender: user research
Interview about book selection habits, reading patterns, and what makes a book work or fail. Input for the book recommender scoring algorithm.
experiments
Key phrase extraction prototype
Extract key phrases from 10 garden items using Ollama, compare LLM-based extraction with YAKE.
experiments
Setting up local embedding models
How to install and run embedding models locally using Ollama, compare three models on garden content, and run a full-scale embedding pass.