Hacker News with Generative AI: Explainability

Explaining Large Language Models Decisions Using Shapley Values (arxiv.org)
The emergence of large language models (LLMs) has opened up exciting possibilities for simulating human behavior and cognitive processes, with potential applications in various domains, including marketing research and consumer behavior analysis.
LLMs struggle to explain themselves (jonathanychan.com)
Explainability is not a game (cacm.acm.org)
A.I.'S Black Boxes Just Got a Little Less Mysterious (nytimes.com)
How LLMs Work, Explained Without Math (miguelgrinberg.com)