As GPT-4 Released, here some of the potential capabilities

amoon

Elite Member
Joined
May 16, 2015
Messages
2,358
Reaction score
1,920


cLs8QVE




-Visual IQ test:

yes, the ones that humans take!

-OCR-free reading comprehension:

input a screenshot, scanned document, street sign, or any pixels that contain text. Reason about the contents directly without explicit OCR. This is extremely useful to unlock AI-powered apps on multimedia web pages, or “text in the wild” from real world cams.

-Multimodal chat:

have a conversation about a picture. You can even provide “follow-up” images in the middle.

-Broad visual understanding abilities,

like captioning, visual question answering, object detection, scene layout, common sense reasoning, etc.

-Audio & speech recognition:

wasn’t mentioned in Kosmos-1 paper, but Whisper is already an OpenAI API and should be fairly easy to integrate.



.
 
Building a complete Auto Dating site that squeeze simps money, running solely on GPT 4 .

Btw , That visual recognition is dope!

the version 4 is just the beginning,
but yeah now that version accept images as inputs, wounder if voice and videos is getting accepted as inputs too, would completely change the tech industry
 
I'm curious about the next step, but I think the difference between the versions will get less and less.
 
It is not available in Free accounts, can anyone confirm this?
 

Attachments

  • Bildschirm­foto 2023-03-15 um 13.24.20.png
    Bildschirm­foto 2023-03-15 um 13.24.20.png
    140.6 KB · Views: 52
I hope they slow down a bit so that I have time to leverage
 
Building a complete Auto Dating site that squeeze simps money, running solely on GPT 4 .

Btw , That visual recognition is dope!
I think replika was already doing this, but they had to train their own AI to bypass all the limitations and NSFW filters. eventually they had to scale back because they got into problem with italy regulator
 
Back
Top