From 1eb285b8745c574c7ecc6f880f452dae1fc194c8 Mon Sep 17 00:00:00 2001 From: dkqjrm Date: Wed, 6 Aug 2025 09:31:41 +0900 Subject: [PATCH] fix: correct typo in docs/format.md Fix duplicate text in safety warning where 'You should We recommend' should be just 'We recommend'. --- docs/format.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/format.md b/docs/format.md index a03aae8..7ec0113 100644 --- a/docs/format.md +++ b/docs/format.md @@ -305,7 +305,7 @@ And the actual answer is: ``` **Important:** -The model has not been trained to the same safety standards in the chain-of-thought as it has for final output. You should We recommend not to show the chain-of-thought to your users as they might contain harmful content. [Learn more in the model card](https://openai.com/index/gpt-oss-model-card/). +The model has not been trained to the same safety standards in the chain-of-thought as it has for final output. We recommend not to show the chain-of-thought to your users as they might contain harmful content. [Learn more in the model card](https://openai.com/index/gpt-oss-model-card/). #### Handling reasoning output in subsequent sampling