How confessions can keep language models honest

媒体报道 OpenAI 原文语言:英文

原文摘录

OpenAI researchers are testing “confessions,” a method that trains models to admit when they make mistakes or act undesirably, helping improve AI honesty, transparency, and trust in model outputs.

以下是来源提供的简短摘录,完整内容请查看原文。

参考来源

← 返回每日AI报告