Hey there everyone, now that AI can "see" very well with GPT-V, I was wondering if it can interact with a computer like we do, just by looking at it. Well, one of the shortcommings of GPT-V is that it cannot really pinpoint the x,y coordinates of something in the screen very well, but I solved it by combining it with simple OCR, and annotating for GPT-V to tell where it wants to click
Turns out with very few lines of code the results are already impressive, GPT-V can really control my computer super well and I can as it to do whatever tasks by itself, it clicks around, type stuff and press buttons to navigate
yes actually, but I only saw it after I've implemented it, I had actually searched for something like that before but I guess Google is worse and worse those days
however, I tried self-operating-computer, and it could not find the right x,y positions on the screen executes the task as effectively
If you look closely it actually does give multiple instructions per screenshot! However it cannot get too far, because the screen changes under it. For example when it starts typing a tweet, the tweet box expands and the send button moves, so it tries to click it but it's not longer there, it needs to take another screenshot to see because it's kinda executing those steps "in the dark"
we could try to patch an "interpolation" kinda of thing for change, but also, I'm curious to see if the multi-modal models that are coming out supporting video would be able to actually just "watch the video" in real time, this would be the ultimate solution
Nice work, I was looking for this for a while and no time to do it myself. I would say it's probably a good idea to make it ai-assisted ; many things you can do faster yourself by saying 'click h2' , fill in text 'hello world' etc instead of having the LLM figure it out. So a combination of things basically. But very good start!
Edit; also probably good to, in case it is not sure, to open the browser and try there.
indeed! Ideally I want it to have very real time human-machine feedback, so you can interrupt it in the middle, point at things, then ask new things, and so on, kinda like if there is someone else pairing with you, and you are telling them to do stuff and course correcting
need to figure out the right UX to do that, and I think the multi-modal models also need to get a bit faster
10 comments
[ 2.9 ms ] story [ 30.2 ms ] threadTurns out with very few lines of code the results are already impressive, GPT-V can really control my computer super well and I can as it to do whatever tasks by itself, it clicks around, type stuff and press buttons to navigate
Would love to hear your thoughts on it!
however, I tried self-operating-computer, and it could not find the right x,y positions on the screen executes the task as effectively
Nice work too!
thanks vim!
For example in the twitter screenshot, it could use just the one image.
we could try to patch an "interpolation" kinda of thing for change, but also, I'm curious to see if the multi-modal models that are coming out supporting video would be able to actually just "watch the video" in real time, this would be the ultimate solution
Edit; also probably good to, in case it is not sure, to open the browser and try there.
need to figure out the right UX to do that, and I think the multi-modal models also need to get a bit faster