GitHub/quartz
1
0
Fork 2
mirror of https://github.com/jackyzha0/quartz.git synced 2025-12-20 03:14:06 -06:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Make spoiler callout foldable

Browse Source
This commit is contained in:
Daniel Balcells 2025-03-03 16:33:35 -05:00
parent 59b668aa79
commit 65b155f0cc
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
content/research/Can AI Models Predict What Youll Say Next.md
View File

@ -26,6 +26,9 @@ This creates a clear, verifiable reward signal for social understanding: either
This benchmark also allows us to test whether models specifically optimized for technical reasoning excel at social understanding, and to get a granular, quantifiable understanding of models' social reasoning abilities. This benchmark also allows us to test whether models specifically optimized for technical reasoning excel at social understanding, and to get a granular, quantifiable understanding of models' social reasoning abilities.
## Prior work and inspiration
## Methodology ## Methodology
### Dataset Creation ### Dataset Creation
@ -59,8 +62,8 @@ We ended up with 123 snippets—below is an example:
> - C) yeah and we could even gamify the process, giving users points for when their honcho makes decisions that align with what they would've done > - C) yeah and we could even gamify the process, giving users points for when their honcho makes decisions that align with what they would've done
> - D) ohh yeah like a more proactive approach as opposed to being bayesian, updating priors based on new information > - D) ohh yeah like a more proactive approach as opposed to being bayesian, updating priors based on new information
> [!warning] Correct answer > [!question]- Can you guess the right answer?
> D > D! Classic Vince being Bayesian.
### Context Modes ### Context Modes