Search Results for author:
Found 3 papers, 1 papers with code
Forbidden Facts: An Investigation of Competing Objectives in Llama-2
LLMs often face competing pressures (for example helpfulness vs. harmlessness).
Cliff-Learning
We conduct an in-depth investigation of foundation-model cliff-learning and study toy models of the phenomenon.
Adversarial Policies Beat Superhuman Go AIs
The core vulnerability uncovered by our attack persists even in KataGo agents adversarially trained to defend against our attack.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
