pith. sign in

Teun van der Weij

Identifiers

  • name variant Teun van der Weij 0.60 · backfill

Papers (5)

  1. SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents cs.AI · 2025 · author #4
  2. The Elicitation Game: Evaluating Capability Elicitation Techniques cs.AI · 2025 · author #2
  3. AI Sandbagging: Language Models can Strategically Underperform on Evaluations cs.AI · 2024 · author #1
  4. Extending Activation Steering to Broad Skills and Multiple Behaviours cs.LG · 2024 · author #1
  5. Evaluating Shutdown Avoidance of Language Models in Textual Scenarios cs.CL · 2023 · author #1

Mentions

  • 2502.02180 #2 · arxiv_oai · confidence 0.70 Teun van der Weij
  • 2506.15740 #4 · arxiv_oai · confidence 0.70 Teun van der Weij
  • 2406.07358 #1 · arxiv_oai · confidence 0.70 Teun van der Weij
  • 2403.05767 #1 · arxiv_oai · confidence 0.70 Teun van der Weij
  • 2307.00787 #1 · arxiv_oai · confidence 0.70 Teun van der Weij

Frequent Coauthors