Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Computer Use is 45x more expensive than structured APIs

reflex.dev

Post reply on HN
Print view View original

71–80 of 295 posts

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

#71

Post by ai_fry_ur_brain »

planb wrote: post #23
aurareturn wrote: post #8

In 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 will not happen. None of the existing apps people use daily on their phones have any incentive to support this. Social media wants the people to doomscroll, shopping apps and booking sites want to use their own dark patterns to make people believe they get a special discount if they buy _now_ and everything else just wants users to see the ads. Why on earth would they offer convenient hooks for AI chatbots?

These people are delusional and want to build a world thats convenient for them to accomplish things lazily with LLMs.

There are no shortcuts in life and its just expensive text autocomplete.

"Lets spin up $750k in GPUs full throttle to scrape a web page with my $200.00 CC subscription."

Everyone is delusional.

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

#72

Post by ctoth »

merlindru wrote: post #44

I'm building something that fixes this exact problem[1]. The landing page doesn't advertise it yet, but essentially, I give agents a small set of tools to explore apps' surfaces, and then an API over common macOS functions, especially those related to accessibility. The agent explores the app, then writes a repeatable workflow for it. Then it can run that workflow through CLI: `invoke chrome pinTab` Why accessibility…

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.

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

#73

Post by ai_fry_ur_brain »

jacktu wrote: post #62

Totally agree. I’ve been building an AI visual tool recently and experimented with both approaches. The latency and c ost of generic "agentic" browser use are absolute dealbreakers for real-time consumer apps right now. Structured APIs (even just chained LLM calls with strict JSON schemas) are not only 40x cheaper, but more importantly, they are deterministic enough to actually build a stable product on top of. Compu…

"Agentic engineering" were always just FADs to bring in more revenue for token providers.

If I think an LLM is good for something I create well defined, very deterministic "middleware" for that purpose on top of Openrouter.

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

#74

Post by airstrike »

aurareturn wrote: post #8

In 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.

It doesn't need to be mobile. The AI-first OS will be headless, undoubtedly.

Humans would be the second-class users of said OS, which can generate UIs on demand as needed.

I've thought about this quite a bit. Started implementing as a side project, but I have too many side projects at the moment...

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

#75

Post by merlindru »

ctoth wrote: post #72
merlindru wrote: post #44

I'm building something that fixes this exact problem[1]. The landing page doesn't advertise it yet, but essentially, I give agents a small set of tools to explore apps' surfaces, and then an API over common macOS functions, especially those related to accessibility. The agent explores the app, then writes a repeatable workflow for it. Then it can run that workflow through CLI: `invoke chrome pinTab` Why accessibility…

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.

i think this goes both ways too :) agents have been a boon for everyone with disabilities, carpal tunnel, RSI, ADHD, anything

and now the fact that interfaces need to be accessible to agents, not just humans, ironically increases it for humans in return

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

#77

Post by aurareturn »

planb wrote: post #23
aurareturn wrote: post #8

In 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 will not happen. None of the existing apps people use daily on their phones have any incentive to support this. Social media wants the people to doomscroll, shopping apps and booking sites want to use their own dark patterns to make people believe they get a special discount if they buy _now_ and everything else just wants users to see the ads. Why on earth would they offer convenient hooks for AI chatbots?

  Why on earth would they offer convenient hooks for AI chatbots?
Competition. If I ask my OS-level AI assistant to find a social media reel about a elephant dancing, the social media app that exposes a set of APIs for an AI agent might get used more.

Watch how fast Meta adds this if a new hot shot social media app succeeds by designing for AI agents controlled by users.

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

#78

Post by jnwatson »

aurareturn wrote: post #8

In 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.

Android is working on it. See AppFunctions.

https://developer.android.com/ai/appfunctions

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

#79

Post by wahnfrieden »

ai_fry_ur_brain wrote: post #73
jacktu wrote: post #62

Totally agree. I’ve been building an AI visual tool recently and experimented with both approaches. The latency and c ost of generic "agentic" browser use are absolute dealbreakers for real-time consumer apps right now. Structured APIs (even just chained LLM calls with strict JSON schemas) are not only 40x cheaper, but more importantly, they are deterministic enough to actually build a stable product on top of. Compu…

"Agentic engineering" were always just FADs to bring in more revenue for token providers. If I think an LLM is good for something I create well defined, very deterministic "middleware" for that purpose on top of Openrouter.

It’s not a fad or without value.

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

#80

Post by k__ »

ai_fry_ur_brain wrote: post #73
jacktu wrote: post #62

Totally agree. I’ve been building an AI visual tool recently and experimented with both approaches. The latency and c ost of generic "agentic" browser use are absolute dealbreakers for real-time consumer apps right now. Structured APIs (even just chained LLM calls with strict JSON schemas) are not only 40x cheaper, but more importantly, they are deterministic enough to actually build a stable product on top of. Compu…

"Agentic engineering" were always just FADs to bring in more revenue for token providers. If I think an LLM is good for something I create well defined, very deterministic "middleware" for that purpose on top of Openrouter.

Agentic engineers can build well defined, very deterministic middleware on top of OpenRouter.

Anthropic even says, that an agent based solution should only be your last resort and that most problems are well served with a one-shot.

https://www.anthropic.com/engineering/building-effective-age...

Post reply on HN