[dead]
Computer Use is 45x more expensive than structured APIs
201–210 of 295 posts
Re: Computer Use is 45x more expensive than structured APIs
#202We gave up on structured APIs 20+ years ago when JSON RPC largely replaced XML REST. You can do REST in many different formats, it mainly just needs to be structured data and self-discoverable. Had we not made that wrong turn, LLMs and humans would have a much easier time reasoning about APIs they don't directly control.
Yeah but why would we keep that around for 20 years with no good use case
Why do you assume theres no good use case?
trpc, grpc, etc are all attempts to add schemas back into JSON. Swagger, OpenAPI, etc are attempts to add discover ability back into JSON-based RPC APIs.
MCPs fall in here as well, which attempt to add schemas and discover ability back in where our APIs aren't actually RESTful.
Re: Computer Use is 45x more expensive than structured APIs
#203[dead]
Re: Computer Use is 45x more expensive than structured APIs
#204Earlier quoted context omitted.
It's really weird, I'm seeing across the board that people who never believed in them before are suddenly all into good software eng practices (starting with writing a spec) because of AI. It's kind of fascinating that we never were willing to do these things for humans but now that AI needs it ... we are all in. A bit depressing in the sense that I think mostly the reason we happy to do it for AI is that we perceive…
My manager just told me that after 12 years of trying to get one of the founders to understand the difference between dev docs and user docs, they tried getting Claude to do it and he finally got it that they are different. He'd been saying this whole time that customer could just read the dev docs. If they could they wouldn't need our software.
How firm is the boundary between a dev doc and a user doc in your opinion? I have found that the overlap can be quite large if the users are also technically proficient. Right now I'm trying to balance "how X works so you can use the app better" with "how X works so you can contribute or build your own plugin". DeepWiki really helps as a backstop for anything not already covered though it's not without its own caveats of course.
Re: Computer Use is 45x more expensive than structured APIs
#205Great guidance hidden in here for making it expensive for agents to navigate your website. Move elements on screen as the mouse moves, force natural mouse movement to make the UI work, change the button labels in the JS to be randomly named every visit, force scrolling to the bottom of the screen to check for hidden extra tasks... Hang on, that sounds like common corporate SaaS apps.
It's really weird, I'm seeing across the board that people who never believed in them before are suddenly all into good software eng practices (starting with writing a spec) because of AI. It's kind of fascinating that we never were willing to do these things for humans but now that AI needs it ... we are all in. A bit depressing in the sense that I think mostly the reason we happy to do it for AI is that we perceive…
Better commit messages, better and more up to date docs, etc. It's not all slop!
Re: Computer Use is 45x more expensive than structured APIs
#206All the websites currently blocking Claude Code or other AI agents are fighting a losing battle. Computer-use is in the early stages, and the thing preventing mass-adoption seems to be the number of tokens it takes. Agents can fumble around trying 10 CLI commands that don't work before finding the right one and we barely notice. But other visual agents (browser use / computer use etc) end up eventually fumbling on to…
They don’t need to be 100% effective they just need to make you afraid enough of being banned to not bother trying.
How do they know that the "you" accessing the site is the same "you" they previously banned?
Face-scanning? Iris patterns?
Re: Computer Use is 45x more expensive than structured APIs
#207Bh
Re: Computer Use is 45x more expensive than structured APIs
#208[flagged]
Re: Computer Use is 45x more expensive than structured APIs
#209Earlier quoted context omitted.
If agents is what it finally takes to get good a11y I'll take it. I'll bitch about it, but I'll take it.
Very real risk of this going in reverse: people building inaccessible websites to prevent AI use.
Or human engineers limiting AI-consumable documentation to improve job security!
Re: Computer Use is 45x more expensive than structured APIs
#210In what world would a vision agent be the default, when whatever HTTP-based mechanism a site uses to communicate with the server can usually be reverse-engineered and easily emulated with widely available HTTP request libraries, HTML parsers, and JavaScript engines, and at worst you can use something like Puppeteer to navigate and control applications at a significantly higher level than image scraping and simulating user input?
It seems like you'd need a deliberately hostile app before a vision agent would even be considered as an option.