Hello,
I just did some testing and I am unable to replicate any capabilities described on this page: https://openai.com/index/hello-gpt-4o/
Here are some screenshots:
Anybody knows why is this? Are these capabilities not live yet? As you see in the screenshots I am using GPT-4o, which is supposed to be multimodal an handle the use cases described…
Yea, also the new voice/video mode is not there
Yes, they communicated that video/voice mode is not yet available. But the examples I am referring to, are not using video/voice…
I would really like to know who the samples on https://openai.com/index/hello-gpt-4o/ (section Exploration of capabilities) were produced as I am unable to replicate them neither with ChatGPT app nor with API…
Were they using some internal tools, which are not yet accessible to the users?
