Phuong, M. et al. (Google DeepMind — developer evaluating its own model), Evaluating Frontier Models for Dangerous Capabilities, arXiv:2403.13793 (2024)

https://arxiv.org/abs/2403.13793

Authors. Phuong, M. et al. (Google DeepMind — developer evaluating its own model)

Venue. arXiv:2403.13793

How the Institute flags it

frontier 1 time

Cited on 1 page

• AI Governance