Judd Rosenblatt

According to our database, Judd Rosenblatt authored at least 3 papers in 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Towards Safe and Honest AI Agents with Neural Self-Other Overlap.

Marc Carauleanu, Michael Vaiana, Judd Rosenblatt, Cameron Berg, Diogo Schwerz de Lucena

CoRR, 2024

Unexpected Benefits of Self-Modeling in Neural Systems.

Vickram N. Premakumar, Michael Vaiana, Florin Pop, Judd Rosenblatt, Diogo Schwerz de Lucena, Kirsten Ziman, Michael S. A. Graziano

CoRR, 2024

Rethinking harmless refusals when fine-tuning foundation models.

Florin Pop, Judd Rosenblatt, Diogo Schwerz de Lucena, Michael Vaiana

CoRR, 2024