Confusing title? "Computer Use" is actually "Browser vision"?
Computer Use is 45x more expensive than structured APIs
31–40 of 295 posts
Re: Computer Use is 45x more expensive than structured APIs
#32In 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 still have to understand what my AI agents could do that I don't want to do myself. Buy stuff? No thanks, I want to see what I buy. I think that they are 99% a solution in search of a problem.
Re: Computer Use is 45x more expensive than structured APIs
#33I think one main point is that not all "computer use" is the same, the harness and agentic experience matters a lot. A poorly designed API experience can actually be _less_ efficient than a well designed browser or computer use experience
In particular, the vision-based approach used in the evaluation has clear limitations with regard to efficiency due to its nature (small observation window, heterogeneous modality)
At Smooth we use an hybrid DOM/vision approach and we index very strongly on small models. An interesting fact is that UIs are generally designed to minimize ambiguity and supply all and only the necessary context as token-efficient as possible, and the UX is cabled up to abstract the APIs in well-understood interface patterns e.g. dropdowns or autocompletes. This makes navigation easier and that's why small models can do it, which is another dimension that must be considered
We typically recommend using APIs/MCP where available and well designed, but it's genuinely surprising how token-efficient agentic browser navigation can actually be
Re: Computer Use is 45x more expensive than structured APIs
#34I 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.
I think it's the third or forth time I see you bragging about HN how many apps you're able to develop with AI now. Care to link any of them, especially where we can see the actual code that you've produced here? Without being able to see actual results, I'm not sure what you want people to take away from your repeated comments.
I only write here because people are spreading doomerism here with AI and I am excited about future.
Well I am competing with geoip provider like maxmind.
I developed custom traceroute and ping service to geolocate IPs with very high accuracy beating products like digital element, maxmind, ipinfo
These companies have huge teams. But my 3 people company already beat them.
Code doesn't matter much, it's not an opensource project.
My free app is http://macrocodex.app which I've developed along with a fitness coach.
I am currently beating companies with 20-30 developers and closing more deals while having 1/10th of the staff.
I am simply very excited about all this.
Nobody cares show you solve the problem, or if your code is ugly. As long as it's reliable and without downtime, you aren't breaking things and causing your customer headache, you are winning.
Even before AI, bad code existed. Not every company had 10x developer writing beautiful idiomatic rust code.
AI is just a tool, people who are trying to generate whole codebase with it are doing something very wrong. You can write code faster with AI provided you understand its strength and weakness
Re: Computer Use is 45x more expensive than structured APIs
#35Isn'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
imagine, if you will, that we had a windowing system that's built on Postscript... lots of folks thought it was a super awesome idea, and built NeXTSTEP around it.
https://en.wikipedia.org/wiki/Display_PostScript
or even one based on PDF like OSX: https://en.wikipedia.org/wiki/Quartz_2D
Re: Computer Use is 45x more expensive than structured APIs
#36In 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.
"In an agentic world, the OS needs to be completely rethought" - if AI is progressing as fast as we think it is, I don't think we'll be interested in waiting for the world to rebuild all the legacy tooling from the OS up. For new stuff, that'd be great.
I imagine the AIs will get a lot better at intercepting things at an intermediate level - API calls under the hood, etc. Probably much better (and cheaper) vision abilities, and perhaps even deeper integration into the machine code itself. It's really hard to anticipate what an advanced model will be capable of 5 years from now.
Re: Computer Use is 45x more expensive than structured APIs
#37I've been thinking of things I'd want an agent for recently. The problem is, everything I think of is something that requires using quite a few different websites, saving a lot of data securely, and working with a lot of sensitive accounts (my email, etc.)
The problem is, all the tasks are essentially: a) things agents probably just can't do, and b) things that absolutely cannot afford to be hallucinated or otherwise fucked up. So far the tasks I've thought of:
- Taxes. So it needs a lot of sensitive information to get W2's. Since I have to look up a lot of this stuff in the physical world anyway, it's not like I can just let it run wild.
- Background check for a new job. It took me 3 hrs to fill out one of them (mostly because the website was THAT bad). Being myself, I already was making mistakes just forgetting things like move in dates from 10 years ago, and having to do a lot of searching in my email for random documents. No way I'm trusting an agent with this.
- Setting up an LLC. Nope nope nope. There's a lot of annoying work involved with this, but I'm not trusting an LLM to do this.
Anyway, I guess my point is that even if an LLM was good at using my computer (so far, it seems like it wouldn't be), the kind of things I'd want an agent for are things that an LLM can't be trusted with.
Re: Computer Use is 45x more expensive than structured APIs
#38The best use cases I've seen for computer/browser use is for legacy SaaS/Software. For example, hotels use archaic Property Management Systems (PMS) and they're required by corporate to use it and pay for it. These companies can barely keep the product alive, they definitely aren't incentivized to maintain an API. In such a case browser use agent seems to be the best (only) way.
Re: Computer Use is 45x more expensive than structured APIs
#39In 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.
[dead]
Re: Computer Use is 45x more expensive than structured APIs
#40In 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.
One of the most seductive (and destructive) forces in software is the desire to rewrite from scratch because rewrites never, ever, ever go as planned. With AI, we're now thinking it's a good idea to rewrite the entire platform from the ground-up. Wild.
except every single piece of progress that we have is the result of trying to do things a different way. so unless you really think we've reached the pinnacle of operating system design, there has to be some room for this?