From 65b155f0cca0d83c7800f044f19ec9e163a606e5 Mon Sep 17 00:00:00 2001 From: Daniel Balcells Date: Mon, 3 Mar 2025 16:33:35 -0500 Subject: [PATCH] Make spoiler callout foldable --- .../research/Can AI Models Predict What Youll Say Next.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/content/research/Can AI Models Predict What Youll Say Next.md b/content/research/Can AI Models Predict What Youll Say Next.md index 0b4839cec..9d355e455 100644 --- a/content/research/Can AI Models Predict What Youll Say Next.md +++ b/content/research/Can AI Models Predict What Youll Say Next.md @@ -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. +## Prior work and inspiration + + ## Methodology ### 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 > - D) ohh yeah like a more proactive approach as opposed to being bayesian, updating priors based on new information -> [!warning] Correct answer -> D +> [!question]- Can you guess the right answer? +> D! Classic Vince being Bayesian. ### Context Modes