🐦 微软的 Azure OpenAI 有一套内容过滤机制,测试了下发现色情和自毁倾向的内容可以很容易地触发。
https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/content-filter https://t.co/Y4xJZswBpc
↩ #tweet
https://learn.microsoft.com/en-us/azure/cognitive-services/openai/concepts/content-filter https://t.co/Y4xJZswBpc
↩ #tweet