The Counterfactual
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
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
•
Sean Trott
4
Share this post
Reflections: my class about LLMs and Cognitive Science
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
6
Results from poll #3 (and updates)
Tokenization's a winner, plus some administrative updates.
Apr 11
•
Sean Trott
3
Share this post
Results from poll #3 (and updates)
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
The Counterfactual's poll #3
The poll for April, 2024
Apr 4
•
Sean Trott
3
Share this post
The Counterfactual's poll #3
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
Modifying readability, pt. 2: the human study
Validating LLM-modified text excerpts with human ratings.
Apr 1
•
Sean Trott
Share this post
Modifying readability, pt. 2: the human study
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
4
March 2024
LLMs and the "not" problem
Negation, understanding, and time to reflect
Mar 19
•
Sean Trott
6
Share this post
LLMs and the "not" problem
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
2
Newsletter updates
LLMs en español; podcasts; and ongoing projects
Mar 12
•
Sean Trott
3
Share this post
Newsletter updates
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
"Cheap tricks" in human language comprehension
When "good enough" is all you need.
Mar 4
•
Sean Trott
6
Share this post
"Cheap tricks" in human language comprehension
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
February 2024
Modifying readability with large language models (pt. 1)
Can GPT-4 Turbo rewrite texts to make them easier or harder to read?
Feb 29
•
Sean Trott
1
Share this post
Modifying readability with large language models (pt. 1)
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
GPT-4 is "WEIRD"—what should we do about it?
When we use LLMs as "model organisms", which humans are we modeling? And how can we overcome the problem of unrepresentative data?
Feb 12
•
Sean Trott
3
Share this post
GPT-4 is "WEIRD"—what should we do about it?
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
5
Results from poll #2
"Modifying readability with LLMs" is a winner
Feb 8
•
Sean Trott
3
Share this post
Results from poll #2
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
2
The Counterfactual's poll #2
The poll for February, 2024.
Feb 5
•
Sean Trott
1
Share this post
The Counterfactual's poll #2
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
Measuring the "readability" of texts with Large Language Models
Defining, operationalizing, and measuring readability is a challenge—can LLMs help?
Feb 2
•
Sean Trott
5
Share this post
Measuring the "readability" of texts with Large Language Models
seantrott.substack.com
Copy link
Facebook
Email
Note
Other
6
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts