This is obvious. The problem is that not everything has an API, while everything has a human-oriented UI.
Computer Use is 45x more expensive than structured APIs
11–20 of 295 posts
Re: Computer Use is 45x more expensive than structured APIs
#12In an agentic world, the OS needs to be completely rethought. For example, every single app functionality should be exposable via an API while remaining human friendly. I think OpenAI designing their own phone is the next logical step. I hope they succeed which should bring major competition to Apple and Android.
> I think OpenAI designing their own phone is the next logical step. I hope they succeed which should bring major competition to Apple and Android.
This is not going to happen, or if it does it will just be Android (like Samsung reskins/modifies it) and it will certainly use Google Play Services.
Re: Computer Use is 45x more expensive than structured APIs
#13In an agentic world, the OS needs to be completely rethought. For example, every single app functionality should be exposable via an API while remaining human friendly. I think OpenAI designing their own phone is the next logical step. I hope they succeed which should bring major competition to Apple and Android.
Openai should not design a phone... They should try making money first
Nonsense. Don't you know how bubbles work? Everyone does massive rushes for all the low hanging and medium hanging fruit. The the bubble pops and the randomized carnage of companies big and small being destroyed is sifted through by the next wave of companies actually intended to make money.
The good ideas and the bad ideas don't signal success in a bubble, nor does making money or not. Its random and any notion of "this was a good business model and that was bad" is post-hoc rationalization. The number of people who make fun of pets.com but order from chewy.com is a prime example of this.
Re: Computer Use is 45x more expensive than structured APIs
#14In an agentic world, the OS needs to be completely rethought. For example, every single app functionality should be exposable via an API while remaining human friendly. I think OpenAI designing their own phone is the next logical step. I hope they succeed which should bring major competition to Apple and Android.
Presumably on Linux at least apps could just expose a DBus API? The machinery for this is already in place as far as I can tell.
Re: Computer Use is 45x more expensive than structured APIs
#15In an agentic world, the OS needs to be completely rethought. For example, every single app functionality should be exposable via an API while remaining human friendly. I think OpenAI designing their own phone is the next logical step. I hope they succeed which should bring major competition to Apple and Android.
This is like insisting - after the problem turns out to be harder than thought - that the worlds roads need to be completely redone to make them self driving friendly, so self driving can work.
Isn’t the whole ‘promise’ of AI that it doesn’t need any of those things?
Re: Computer Use is 45x more expensive than structured APIs
#16Isn't it possible to somehow wire this into the window manager? Wayland or whatever. Have it speak the native window lang rather than crunch the pixels? At least for the majority.
I can see the appeal in pixel route given universality but wow that seems ugly on efficiency
Re: Computer Use is 45x more expensive than structured APIs
#17> This is not a model problem. The vision agent was reasoning about a rendered page and had no signal that the page wasn't showing everything. > To make the comparison apples-to-apples, we rewrote the vision prompt as an explicit UI walkthrough, naming the sidebar items, tabs, and form fields the agent should interact with at each step. Fourteen numbered instructions covering the navigation the agent had failed to fi…
This is a fair point.
The models frequently failed for many reasons on earlier runs, and the browser-use prompt ended up being pretty granular. I'll add a couple of runs that include a scroll instruction to the repo today and see how that compares
Pretty hard to guess what Anthropic trained sonnet on, but general multimodals are what people are using to drive similar tools today, whether GUI-trained or not, so the comparison still holds, for now
Re: Computer Use is 45x more expensive than structured APIs
#18In an agentic world, the OS needs to be completely rethought. For example, every single app functionality should be exposable via an API while remaining human friendly. I think OpenAI designing their own phone is the next logical step. I hope they succeed which should bring major competition to Apple and Android.
Everything exposed programmatically would have been great even without agents—the NixOSes and Emacses of the world show just how amazing a fully flexible and programmable world would be—but I'm glad that the advent of AI is getting people invested in this vision :P
Re: Computer Use is 45x more expensive than structured APIs
#19What i don't understand about "computer use" is why they're not just grabbing the window handles and storing them to determine what should be clicked after the first few iterations of using that a specific application. if a new case / path / whatever is found, drop back to screen grabbing and bounding boxes and then figure the handles that are there and store after.
idk.. not really thought out too much, but has to be better
Re: Computer Use is 45x more expensive than structured APIs
#20I saw Codex was screenshotting, then clicking around. I just stopped it and never used that again.
Using CLI tools is much faster and token-efficient. I developed ten apps in the last two months. One reached 10,000+ monthly active users.
I ask Codex to generate SVG line by line and backtrack edit, ask it to use Inkscape to generate icons, etc...
I developed all this on $20 codex sub.