· · AI Alignment Forum
AI Model Evaluation Risks Amplifying Undesired Behaviors
This is the first in a series of research updates from the Google DeepMind Language Model Interpretability team, in interpretability and adjacent areas. TL;DR It's often assumed that models will act more aligned when they can tell they're being evaluated. But we find that Gemini can take “undesired”
#ai#model evaluation#deepmind#interpretability#india ai market