One Thousand Faces
Subscribe
Sign in
Home
Notes
Archive
About
WikiBench: 76% of SOTA Models Fail
Assessing real-world understanding and agentic tool use with a twist on a classic game.
Aug 1
•
Hero Thousandfaces
28
Share this post
One Thousand Faces
WikiBench: 76% of SOTA Models Fail
Copy link
Facebook
Email
Notes
More
5
June 2025
How To Be Funny, Part 2: For AIs and The People That Love Them
So, deep learning walks into a wall... (AKA my gripes with current post-training and benchmark paradigms)
Jun 16
10
Share this post
One Thousand Faces
How To Be Funny, Part 2: For AIs and The People That Love Them
Copy link
Facebook
Email
Notes
More
March 2025
How To Be Funny, Part 1: For Humans
If you've never gotten off a good joke in your life, start here
Mar 12
•
Hero Thousandfaces
19
Share this post
One Thousand Faces
How To Be Funny, Part 1: For Humans
Copy link
Facebook
Email
Notes
More
1
January 2025
Coming soon
This is One Thousand Faces.
Jan 22
•
Hero Thousandfaces
Share this post
One Thousand Faces
Coming soon
Copy link
Facebook
Email
Notes
More
Share
Copy link
Facebook
Email
Notes
More
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts