Notes on Anthropic's Computer Use Ability
composio.dev
Notes on Anthropic's Computer Use Ability
1–10 of 108 posts
Re: Notes on Anthropic's Computer Use Ability
#2Re: Notes on Anthropic's Computer Use Ability
#3For the folks who are more savvy on the Docker / Linux front...
1. Did Anthropic have to write its own "control" for the mouse and keyboard? I've tried using `xdotool` and related things in the past and they were very unreliable.
2. I don't want to dismiss the power and innovation going into this model, but...
(a) Why didn't Adept or someone else focused on RPA build this?
(b) How much of this is standard image recognition and fine-tuning a vision model to a screen, versus something more fundamental?
Re: Notes on Anthropic's Computer Use Ability
#4Re: Notes on Anthropic's Computer Use Ability
#5Re: Notes on Anthropic's Computer Use Ability
#6Re: Notes on Anthropic's Computer Use Ability
#7Well, this just opened up a new phase in the captcha wars.
Re: Notes on Anthropic's Computer Use Ability
#8Re: Notes on Anthropic's Computer Use Ability
#9What are some good use cases for this? Something that a business can be built around
QA...
Re: Notes on Anthropic's Computer Use Ability
#10This is such a idiotic hype-cycle, they just fine-tuned a model over vision API. I really don't understand why everyone is loosing their mind over this