AI & ML interests

None defined yet.

Recent Activity

christopher 
posted an update 22 days ago
view post
Post
423
Something very cool is cooking at Lichess
  • 1 reply
·
christopher 
updated a dataset about 1 month ago
christopher 
published a dataset about 1 month ago
christopher 
updated a Space about 2 months ago
christopher 
published a Space 2 months ago
cfahlgren1 
posted an update 4 months ago
view post
Post
652
I ran the Anthropic Misalignment Framework for a few top models and added it to a dataset: cfahlgren1/anthropic-agentic-misalignment-results

You can read the reasoning traces of the models trying to blackmail the user and perform other actions. It's very interesting!!

cfahlgren1 
posted an update 5 months ago