This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Teun van der Weij
Posts
Sorted by New
18
An Introduction to AI Sandbagging
20d
0
21
Simple distribution approximation: When sampled 100 times, can language models yield 80% A and 20% B?
4mo
0
Wiki Contributions
Comments