mnotgod96 / AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
https://appagent-official.github.io/
MIT License
4.97k stars 538 forks source link

效果不如预期,是则么回事? #33

Open clm971910 opened 9 months ago

clm971910 commented 9 months ago

我尝试了 打电话 和 发邮件2个任务

打电话的任务 卡在来拨号的环节, 发邮件的任务,把收件人地址和内容混在一起了

Zero-coder commented 9 months ago

只能说:有待加强

Zero-coder commented 9 months ago

请问兄弟是Mac运行的还是Ubuntu运行的

clm971910 commented 9 months ago

mac

twiceyuan commented 8 months ago

英文下测试效果还可以,中文下比较差,应该主要受限于 gpt4v 对中文的支持。参考 https://www.robertmao.com/comments/blog/zh/chat-gpt-4-v-first-time-expereince