正文 · 原文
该语言的正文暂不可用，当前显示已有版本。
https://t.co/bpAkCzyO5S
OpenAI 测试模型在战斗情境下的回答是否符合战争法
自动核验发布 · 本文由系统生成并完成证据核验，未经人工审稿。
据 Fortune 报道，OpenAI 让国际专家向模型输入高风险战斗情境提示，再由工程师依据回答与《日内瓦公约》的符合程度调整模型。报道将这项测试与模型供美国军方使用联系起来，但材料没有给出测试结果。
Fortune: OpenAI now tests whether its models' answers obey the laws of war, because those models are going to the U.S. military.
OpenAI created its first human rights and responsible deployment role, Sarah Yager, who spent 30 years on military issues before joining in June, described her method.
International experts entered high-stakes combat prompts into OpenAI models, and then engineers changed the models based on how the answers measured up against the Geneva Conventions.
This is kind of backward finetuning step Yager said had never been taken before.
在 X 查看回复的帖子