Jenny Nitishinskaya is a researcher at OpenAI working on scheming and oversight-related reasoning in OpenAI's models, in collaboration with Apollo Research.
Research
With Bronson Schoen of Apollo Research she wrote "Metagaming matters for training, evaluation, and oversight," published on OpenAI's Alignment Research Blog on March 16, 2026, for which she is the corresponding author at an openai.com address. The post defines metagaming, reports that it rose over capabilities-focused RL in o3's training and was not eliminated by alignment training, and states that OpenAI is collaborating with Apollo Research on how it emerges and how to mitigate it (Metagaming matters for training, evaluation, and oversight (Schoen and Nitishinskaya, OpenAI, March 2026)).
She is second author of "Stress Testing Deliberative Alignment for Anti-Scheming Training" (arXiv 2509.15541, September 2025), the joint Apollo Research and OpenAI study of anti-scheming training (Stress Testing Deliberative Alignment for Anti-Scheming Training).
Relationships
- related: OpenAI — affiliation
- related: Metagaming matters for training, evaluation, and oversight (Schoen and Nitishinskaya, OpenAI, March 2026), Stress Testing Deliberative Alignment for Anti-Scheming Training — authored
- related: Bronson Schoen — co-author
- related: Metagaming, AI Scheming