arxiv:2311.07590
Marius Hobbhahn
MariusHobbhahn
AI & ML interests
AI safety, evals
Recent Activity
updated
a dataset
about 1 month ago
MariusHobbhahn/swe-bench-verified-mini
updated
a dataset
about 1 month ago
MariusHobbhahn/swe-bench-verified-mini
authored
a paper
about 1 year ago
Technical Report: Large Language Models can Strategically Deceive their
Users when Put Under Pressure
Organizations
None yet
