Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Felix Hofstätter
Observed name:
Hofstätter, Felix
Institution:
OpenAI (United States)
Observed institution:
OpenAI (United States)
OpenAlex ID:
A5143413803
AI Sandbagging: Language Models can Strategically Underperform on Evaluations
2024
·
van der Weij, Teun
, Hofstätter, Felix
, et al.
·
arXiv (Cornell University)
·
5
PDF
Stress Testing Deliberative Alignment for Anti-Scheming Training
2025
·
Schoen, Bronson
, Nitishinskaya, Evgenia
, et al.
·
arXiv (Cornell University)
·
2
PDF
Propensities Please: Exposing Alignment-Faking LLMs using Synthetic Document Finetuning
2026
·
Haroen, Ardy
, Lorkowski, Florian
, et al.
·
arXiv (Cornell University)
PDF
Measuring Reward-Seeking via Contrastive Belief Updates
2026
·
Højmark, Axel
, Scheurer, Jérémy
, et al.
·
arXiv (Cornell University)
PDF
Probing and Steering Evaluation Awareness of Language Models
2025
·
Nguyen, Jord
, Hoang, Khiem
, et al.
·
arXiv (Cornell University)
PDF
The Elicitation Game: Evaluating Capability Elicitation Techniques
2025
·
Hofstätter, Felix
, van der Weij, Teun
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
6
Citation count:
7
H-index:
2
I10-index:
Year
Topic
Type
