Detecting and reducing scheming in AI models

Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models. The team shared concrete examples and stress tests of an early method to reduce scheming.

Sep 17, 2025 - 18:00
Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models. The team shared concrete examples and stress tests of an early method to reduce scheming.
Jat AI Stay informed with the latest in artificial intelligence. Jat AI News Portal is your go-to source for AI trends, breakthroughs, and industry analysis. Connect with the community of technologists and business professionals shaping the future.