OpenAI ↗ · 2025-09-17 08:00 · UTC+8
Detecting and reducing scheming in AI models
媒体报道 OpenAI 原文语言:英文
原文摘录
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.
以下是来源提供的简短摘录,完整内容请查看原文。