Open source code for screensharing with GPT-4 Vision and Llava

Posted by Suneel478 on Tuesday December 12, 2023 @10:03AM
from the github.com dept.

https://github.com/suneelmatham/vision-agent

( 1 comment | 2 points | on HN )

Re:Open source code for screensharing with GPT-4 Vision and ... by Suneel478 on Tuesday December 12, 2023 @10:03AM (#38613038)

Open sourcing code for sharing screen with vision language models like gpt-4, Llava and Bakllava. Aim's to develop open agents that can specialize and assist with coding and using complex tools. You can try the demo here - https://vision-agent.synth.co.in Will be posting updates here - https://twitter.com/suneel_matham

[ Parent | on HN ]