Atlas / Reports / Detail
Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework
Model Safety / System Cards report from Amazon with 7 connected researchers in the LLMpeople atlas.
Connected researchers
Researcher
1 reports
Satyapriya Krishna
Amazon
Satyapriya Krishna recently completed a Ph.D. at Harvard SEAS on machine learning explanations and describes past work spanning Amazon, Google DeepMind, and Meta FAIR. Public report authorship also links him to Amazon's frontier model safety work, but his current employer is not clearly stated.
Researcher
2 reports
Ninareh Mehrabi
Amazon
Ninareh Mehrabi says she works at Meta's Superintelligence Labs on red teaming and frontier risks, after earlier roles at Amazon AGI and Amazon Alexa AI. USC CAIS lists her as a PhD alum in computer science.
Researcher
2 reports
Abhinav Mohanty
Amazon
Public sources list Abhinav Mohanty as a coauthor on Amazon Nova safety evaluation work under the Frontier Model Safety Framework.
Researcher
2 reports
Vincent Ponzo
Amazon
Public sources identify Vincent Ponzo as a former Responsible AI Business Development Lead at Amazon AI and a 2025 Amazon technical report coauthor.
Researcher
2 reports
Payal Motwani
Amazon
Public report authorship links Payal Motwani to Amazon Nova Responsible AI evaluations for Nova Premier and Nova 2.0 Lite.
Researcher
2 reports
Rahul Gupta
Amazon
Amazon Science lists Rahul Gupta as Senior Manager, Applied Science at Amazon AGI, with publications in LLM safety, evaluation, and responsible AI.