Archive - The Counterfactual

Ingredients, flavor networks, and the "essence" of cuisine

Trying to understand culinary diversity in terms of common ingredients and flavor networks.

Jul 19 •

"Mechanistic interpretability" for LLMs, explained

Trying to peek inside the "black box".

Jul 8 •

June 2024

How to evaluate statistical claims

Some core lessons from statistics and research methods.

Jun 27 •

Human culture in the age of machines

"Delving", technological determinism, and machine-mediated culture.

Jun 10 •

May 2024

Results from poll #4

May 21 •

The Counterfactual's poll #4

Poll for May, 2024.

May 13 •

Tokenization in large language models, explained

Modern language models predict "tokens", not words—but what exactly are tokens?

May 2 •

April 2024

Reflections: my class about LLMs and Cognitive Science

Class overview, what I felt went well, and what I'd like to change in the future.

Apr 17 •

Results from poll #3 (and updates)

Tokenization's a winner, plus some administrative updates.

Apr 11 •

The Counterfactual's poll #3

The poll for April, 2024

Apr 4 •

Modifying readability, pt. 2: the human study

Validating LLM-modified text excerpts with human ratings.

Apr 1 •

March 2024

LLMs and the "not" problem

Negation, understanding, and time to reflect

Mar 19 •

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts