8 Comments

any development for llama2?

Expand full comment

```So how do we get GPT4V to “see” what’s in the box? We give it back the previous result’s HTML, together with a note to “fill in” the white box with this provided HTML.

And it works.```, Why is this feasible? It looks really incredible. how does chatGPT-4v know which object the arrow point at?it's just a blank white rectangle && original html code? I don't understand, could you explain this? thanks in advance.

Expand full comment

I made a test, using an arrow to point at an area(used a rectangle to mark this area), then gpt-4v generated the new page with a wrong area modification.

I think your current method is not very solid. @linearuncle

Expand full comment

Game... Changer... 🏆

Expand full comment

You have exceeded your available quota, please check

your plan and billing details, giving error

Expand full comment

Love this Steve amazing work.

Expand full comment