Show HN: AI browser ninja that can complete any task on Chrome
Hey folks, so I built a chrome extension called [name redacted], an AI assistant that automatically completes your browser tasks for you. You simply enter your task, and [name redacted] uses GPT-4V to figure out the best browser action to perform next repeatedly until the task is accomplished.
The idea is that you can delegate your personal tasks like online shopping or making reservations to [name redacted]. You can also use him professionally to find leads on LinkedIn, send status updates to your boss, or research your competitors and write an analysis document.
I’m wondering if you would use [name redacted] as part of your daily routine? Would he be more useful in a personal or professional setting? What concerns do you with using a productivity tool like this?
I'm also planning to add voice support and the ability to schedule tasks soon. Do either of these features interest you?
If you want to try [name redacted], download the chrome extension and let me know what you think. It's completely free with no sign up required! I personally wouldn't trust it with anything that involves submitting forms. What if it gets any data wrong? Even watching the demo video made me feel anxious! I guess I'm finally on the other side of this Douglas Adams quote: > Anything that's invented between when you're fifteen and thirty-five is new and exciting and revolutionary and you can probably get a career in it. Anything invented after you're thirty-five is against the natural order of things. I do think it's a cool project though! Yeah RE: Douglas Adams, it is like the early days of internet, where people might not want to enter their credit card details. I think services like this might mean the web needs a way to say "this form is reversible, and so OK for AI to drive it". Example might be unsubscribing from an email, or even ordering something if an order can be cancelled within 24 hours. Maybe the API says "this action can be cancelled within X hours" and then you as a user can decide what sort of actions the AI can do. Totally fair point! We're planning to add a feature where you can record yourself doing some task and then [name redacted] can repeat it for you. Would that you give you more confidence that the AI will do the right thing? We're thinking this feature will useful for automating repetitive actions reliably. How about something similar to how websites say "Allow this site to use your camera" you make it so "Allow this form the be submitted by Genji", once they say yes, next time it doesn't need to ask. Love that idea! And not just forms, there's other actions where users might want to have the opportunity to confirm like making payments. This is cool, but similar to another commenter, I would only use it if I had built myself. But that it makes people uncomfortable means its ahead of its time (it's a compliment). Thank you! Would you be more open to using it if the code was fully open source? I feel like I would only use something like this if I had built it myself.