Detecting and reducing scheming in AI models

Company news OpenAI Source language: English

Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models.

Excerpt

Apollo Research and OpenAI developed evaluations for hidden misalignment (“scheming”) and found behaviors consistent with scheming in controlled tests across frontier models.

Short excerpt from the source — open the original for the full text.

Sources

← Back to the daily brief