-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
idea #66
Comments
@rohanarun Article says "HyperWriteAI" and from this github's own main page: "Ongoing Development |
I mean you are saying you have a custom model, but all I see it's propietary and business products, your custom model is handwritten for the cases, but this is gpt-4V so it's not a rip off, they just had the idea (wouldn't it be cool if gpt-4 could control computers) and open sourced it first 🤷. It can't be a rip off because you started without gpt-4v, you trained a propietary custom model, these guys just did prompt engineering and got it wit gpt-4v to work, without taking any custom models. If these guys get more fame it's because they open sourced it first, and then it's first come first serve. I think it's fair. imho. Also your insecurity is showing, if your product was really good there is no need to spam it on every issue. Just give us something better and people will naturally flock to it. |
Keep posting these will not help. AGI is for everyone, truely democratic. |
@alafortu Thanks for the suggestion. Low accuracy with GPT-4v is a known issue at the moment, and support for other models is planned in the future. |
I played with gpt4V on other projects and it definitely has a hard time figuring out coordinates. I used other model trained on image identification to find the coordinates of the box made around the object detected and then I can pass it to gpt 4 to perform an action. For your use case, I juste tested this model "https://huggingface.co/foduucom/web-form-ui-field-detection" Far from being perfect, but maybe an idea to build on. If you auto computer can detect and get the proper coordinates of the input fields in an image, it could help or at least add a level of redundancy to improve accuracy in clicking and inputing stuff at the right places.
The text was updated successfully, but these errors were encountered: