即刻App年轻人的同好社区
下载
翻旧论文发现，很神奇，原来推理模型反而要大家尽量不要用提示词，甚至会损害模型的能力
When evaluating DeepSeek-R1, we observe that it is sensitive to prompts. Few-shot prompting consistently degrades its performance. Therefore, we recommend users directly describe the problem and specify the output format using a zero-shot setting for optimal results.
When evaluating DeepSeek-R1, we observe that it is sensitive to prompts. Few-shot prompting consistently degrades its performance. Therefore, we recommend users directly describe the problem and specify the output format using a zero-shot setting for optimal results.
0 00
哎即刻能发出这个词了？
是福音啊: 承认自己是个傻逼，确实不懂的太多，懂的太少
1 10
