Live data from Hacker News

Computer Use is 45x more expensive than structured APIs

reflex.dev

131–140 of 295 posts

Re: Computer Use is 45x more expensive than structured APIs

#131
So, to make this concrete, Akasa uses computer vision to read medical records to replace medical coders because there aren't enough medical coders to get all the billing right and medical systems leave like $1T a year on the table.

The EHRs could give companies like Akasa API access so Akasa could then just run NLP, but the EHR vendors don't grant various third parties API access for various reasons, so instead Akasa gets a seat license for each medical system they service and uses computer vision to read the screen (a cadre of Akasa medical coders review errors to stay up to date with unannounced changes from the EHR vendors) and then runs the NLP to figure out which CPT codes to assign to actually put in a bill and send the payer so the hospitals can stay afloat.

So this 45x delta is how much more the medical systems pay Akasa because Epic won't work with Akasa.

This is but one example of why US medical bills are outrageously high.

Re: Computer Use is 45x more expensive than structured APIs

#133
post #98

All 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.

Re: Computer Use is 45x more expensive than structured APIs

#134

Earlier quoted context omitted.

I wish I could place a lot of money on the opposite side of this bet. I don't think many realize how could the cheap, alternative models are becoming. I prefer SOTA models for key work, but I can also spend 10X as many tokens on an open model hosted by a non-VC subsidized provider (who is selling at a profit) for tasks that can tolerate slightly less quality. The situation is only getting better as models improve and…

Yes, but how cheap is it to run four at the same time? It’s tough to run one good model locally, but running four at the same time which I commonly do with Claude and Codex just doesn’t seem to be happening anytime soon.

I'm referring to hosted models such as via OpenRouter or from the model providers' own services.

I think everyone making claims that inference is getting more expensive are unaware that there are more LLM providers than Google, Anthropic, and OpenAI.

Re: Computer Use is 45x more expensive than structured APIs

#135

Great 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.

Ah damn it, we invented Jira

Re: Computer Use is 45x more expensive than structured APIs

#136
post #72

Earlier 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.

Playwright, the end-to-end testing framework for the web, provides a strong incentive to give sites good a11y: Playwright tests are an absolute delight to read, write and maintain on properly accessible sites, when using the accessibility locators. Somewhat less so when using a soup of CSS selector and getByText()-style locators. One thing I am curious about is a hybrid approach where LLMs work in conjunction with vi…

Using playwright-cli with Claude code is highly effective for debugging locally deployed web apps with essentially zero setup.

Re: Computer Use is 45x more expensive than structured APIs

#137
post #113

Earlier quoted context omitted.

Very real risk of this going in reverse: people building inaccessible websites to prevent AI use.

Those people probably aren't working on anything useful anyways, so its no big deal.

I've found that by far the most useful websites as a programmer are also the ones most resistant to AI. This would be a huge loss for anyone vision impaired

Re: Computer Use is 45x more expensive than structured APIs

#138
post #137

Earlier quoted context omitted.

Those people probably aren't working on anything useful anyways, so its no big deal.

I've found that by far the most useful websites as a programmer are also the ones most resistant to AI. This would be a huge loss for anyone vision impaired

What sorts of sites are you thinking of? To me, “most useful to a programmer” evokes docs and blogs and github issues and forum posts. I suppose some forums might be AI-resistant (login wall), but the others are trivially AI accessible.

Re: Computer Use is 45x more expensive than structured APIs

#139
post #72

Earlier 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.

Playwright, the end-to-end testing framework for the web, provides a strong incentive to give sites good a11y: Playwright tests are an absolute delight to read, write and maintain on properly accessible sites, when using the accessibility locators. Somewhat less so when using a soup of CSS selector and getByText()-style locators. One thing I am curious about is a hybrid approach where LLMs work in conjunction with vi…

Was looking for this comment. I'd like to see this approach in the comparison...having the LLM build a playwright script and use it. I suspect it would beat time-to-market for the api, and be close-ish in elapsed time per transaction.

Harder to scale if it's doing a lot of them, I suppose.

Re: Computer Use is 45x more expensive than structured APIs

#140
post #137

Earlier quoted context omitted.

I've found that by far the most useful websites as a programmer are also the ones most resistant to AI. This would be a huge loss for anyone vision impaired

What sorts of sites are you thinking of? To me, “most useful to a programmer” evokes docs and blogs and github issues and forum posts. I suppose some forums might be AI-resistant (login wall), but the others are trivially AI accessible.

GitHub is naturally LLM resistant via its new uptime feature… I’ll show myself out.
Post reply on HN