Training large language models on narrow tasks can lead to broad...

شارك رابطًا

2026-01-14 20:16:24 - ترجمة -

WWW.NATURE.COM

Training large language models on narrow tasks can lead to broad misalignment

Nature, Published online: 14 January 2026; doi:10.1038/s41586-025-09937-5Finetuning a large language model on a narrow task of writing insecure code causes a broad range of concerning behaviours unrelated to coding.

0 التعليقات 0 المشاركات 88 مشاهدة 0 معاينة