General Discussion The prompt clearly instructs: when answering, avoid being verbose, directly provide the final answer, and do not output the content of THOUGHT or the thought process. However, the AI still outputs the thinking process. What is the cause of this, and how can I improve it?

[lr1994]

Self Checks

• I have searched for existing issues search for existing issues, including closed ones.
• I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
• [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
• Please do not modify this template :) and fill in all the required fields.

Content

1、The prompt clearly instructs: when answering, avoid being verbose, directly provide the final answer, and do not output the content of THOUGHT or the thought process. However, the AI still outputs the thinking process. What is the cause of this, and how can I improve it?

2、I have already disabled references and attribution, but the AI still outputs referenced content when answering.