Teun van der Weij
Posts
The Elicitation Game: Evaluating capability elicitation techniques
by Teun van der Weij @ 2025-02-27 | +3 | 0 comments
by Teun van der Weij @ 2025-02-27 | +3 | 0 comments
[Paper] AI Sandbagging: Language Models can Strategically Underperform on...
by Teun van der Weij @ 2024-06-13 | +22 | 0 comments
by Teun van der Weij @ 2024-06-13 | +22 | 0 comments
Beyond Humans: Why All Sentient Beings Matter in Existential Risk
by Teun van der Weij @ 2023-05-31 | +12 | 0 comments
by Teun van der Weij @ 2023-05-31 | +12 | 0 comments