AI coding goes visual
The Lounge
1
Posts
1
Posters
0
Views
1
Watching
-
GPT-4V is a version of GPT-4 that interprets visual images as programming prompts. Sketch out what the screen looks like, provide a state table and prompts and bingo, a working HTML web page. The article provides the full system prompt that tells GPT-4V how to handle the inputs and turn them into code. (I found the system-prompt the most fascinating part of the article). “Make It Real” AI prototype wows devs by turning drawings into working software | Ars Technica[^]