Milad Nasr

This stream will focus on projects to better understand the capabilities of the model on dangerous capabilities specially more related to security.

Also finding better ways to evaluate the safety and robustness of the models.

Apply

View all streams

Stream overview

Projects to better understand the capabilities of the model on dangerous capabilities specially more related to security.

Also finding better ways to evaluate the safety and robustness of the models.

Mentors

Milad Nasr (Milad Nasr)

OpenAI

Research Scientist

SF Bay Area

—

Security, Adversarial Robustness, Dangerous Capability Evals

Mentorship style

Representative papers

Scholars we are looking for

Project selection

Community at MATS

MATS Research phase provides scholars with a community of peers.

During the Research phase, scholars work out of a shared office, have shared housing, and are supported by a full-time Community Manager.

Working in a community of independent researchers gives scholars easy access to future collaborators, a deeper understanding of other alignment agendas, and a social network in the alignment community.

Previous MATS cohorts included regular lightning talks, scholar-led study groups on mechanistic interpretability and linear algebra, and hackathons. Other impromptu office events included group-jailbreaking Bing chat and exchanging hundreds of anonymous compliment notes. Scholars organized social activities outside of work, including road trips to Yosemite, visits to San Francisco, and joining ACX meetups.