现在用截屏作为输入,一是暴露的信息过多,可能有隐私风险;二是大模型在处理大图时,消耗的 Token 和处理的时间较长,导致输入效率较低。如果可以将正在输入的应用、网页等名称,以及其他可以获取到的文本信息,通过文本输入给大模型,这样处理效率会明显提升
Please authenticate to join the conversation.
In Review
Feature Request
About 1 month ago

MeadoWonder
Get notified by email when there are changes.
In Review
Feature Request
About 1 month ago

MeadoWonder
Get notified by email when there are changes.