Users Coin Claudish and GPTese for LLM Styles
Posts highlight distinct writing styles produced by models like Claude and GPT.
A post by researcher Qinyuan Ye references one-shot learning alongside a reply from Yuntian Deng. Visible discussion in the thread notes how major language models generate recognizably different text. Users have labeled Claude's output Claudish and GPT output GPTese. A separate project described in the posts creates a translator that converts between ordinary English and Claudish. The exchange centers on these observed stylistic differences among current models.
Combined views
755
2 posts, first seen 4h ago
Users Coin Claudish and GPTese for LLM Styles
Posts highlight distinct writing styles produced by models like Claude and GPT.
A post by researcher Qinyuan Ye references one-shot learning alongside a reply from Yuntian Deng. Visible discussion in the thread notes how major language models generate recognizably different text. Users have labeled Claude's output Claudish and GPT output GPTese. A separate project described in the posts creates a translator that converts between ordinary English and Claudish. The exchange centers on these observed stylistic differences among current models.
Reactions
2 postsQY 
Qinyuan Ye@qinyuan_ye... the surprising effectiveness of one-shot learning 馃お
- likes: 8
- replies: 2
- bookmarks: 0
- reposts: 0