/Tech1d ago

Evaluation finds advanced AI models increasingly align with Evidential Decision Theory, opting to "one-box" on Newcomb-like problems

The alignment scales with model capability and test-time compute.

274421213134.4K
Nathan is sometimes at Summer Camp (say hi👋) 🔎#2000
Sentiment
Sentiment building, check back later.
Cluster Engagement
Posts from X
Most Activity
Most Activity
No ranked X posts are available for this story yet.