OpenAI ↗ · 2025-09-17 08:00 · UTC+8
Detecting and reducing scheming in AI models
Media reports OpenAI Source language: English
Excerpt
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.
Short excerpt from the source — open the original for the full text.