x

AI ALIGNMENT FORUM

AF

E.Roland — AI Alignment Forum

Roland

Roland

Message

Technical Alignment Researcher, Research@AE Studio, EA@ATL

96

Ω

19

1

10

6y

Roland

Technical Alignment Researcher, Research@AE Studio, EA@ATL

Modular Pretraining Enables Access Control

Full author list: Ethan Roland*, Murat Cubuktepe*, Erick Martinez*, Stijn Servaes, Keenan Pepper, Mike Vaiana, Diogo Schwerz de Lucena, Judd Rosenblatt, Addie Foote, Cem Anil, Alex Cloud; *Equal contribution tldr: Frontier AI models have knowledge that could be misused for nefarious purposes. To address this risk, we introduce Gradient Routed...