This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
2176
Teun van der Weij — AI Alignment Forum
Teun van der Weij
Research scientist at Apollo Research.
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
2
Teun van der Weij's Shortform
8mo
0
57
Stress Testing Deliberative Alignment for Anti-Scheming Training
1mo
10
12
How to mitigate sandbagging
7mo
0
4
The Elicitation Game: Evaluating capability elicitation techniques
8mo
1
35
[Paper] AI Sandbagging: Language Models can Strategically Underperform on Evaluations
1y
0
19
An Introduction to AI Sandbagging
2y
0
21
Simple distribution approximation: When sampled 100 times, can language models yield 80% A and 20% B?
2y
0
Comments