Website streamed live directly from a model • Hacker News Board

Re: Website streamed live directly from a model

#121

Post by potamic » Fri, Apr 24, 2026, 6:12 AM UTC

zan2434 wrote: post #51

martianlantern wrote: post #3

Cool project, but just a side thought I was having about how do people have resources and the money to make things like this and make it avl for public, I mean it's fair to say they have their own GPUs or if they are using api keys for gpt or Gemini with enterprise subsidized inference But still coming from a frugal background I still cannot wrap my head around this

I am unfortunately just paying for this out of pocket! Didn't really expect it to blow up like this.

What's the average cost per interaction?

Re: Website streamed live directly from a model

#122

Post by fennecbutt » Fri, Apr 24, 2026, 3:48 PM UTC

maplethorpe wrote: post #75

jazzypants wrote: post #44

Earlier quoted context omitted.

Do we ever simply accept that LLMs weren't made for this kind of detail-oriented work? I can't imagine something like this ever being anything other than a toy which can't be trusted. Will Silicon Valley executives ever accept this reality? If we acquiesce and admit that LLMs are a good tool for prototyping and boilerplate-reduction, but not finished products-- is that when the bubble finally bursts?

I think the unfortunate fact is that most jobs in the world do not require accuracy, so an inaccurate result has a negligible impact over an accurate one. I used to feel job safety in the knowledge that AI labs weren't likely to solve the hallucination problem. Then it dawned on me that they don't need to — they just need to reduce our collective expectations.

Isn't that entirely analogous to our evolved and lived experiences?

We've never had to act with surgical precision except in matters of math/science/engineering.

Like how you fill up your coffee cup up to a level probably +/- 50ml each morning.

Re: Website streamed live directly from a model

#123

Post by Timwi » Sat, Apr 25, 2026, 1:23 AM UTC

fennecbutt wrote: post #122

maplethorpe wrote: post #75

Earlier quoted context omitted.

I think the unfortunate fact is that most jobs in the world do not require accuracy, so an inaccurate result has a negligible impact over an accurate one. I used to feel job safety in the knowledge that AI labs weren't likely to solve the hallucination problem. Then it dawned on me that they don't need to — they just need to reduce our collective expectations.

Isn't that entirely analogous to our evolved and lived experiences? We've never had to act with surgical precision except in matters of math/science/engineering. Like how you fill up your coffee cup up to a level probably +/- 50ml each morning.

No. For most of human evolution, we were hunter-gatherers. Imagine trying to hunt game with the accuracy of LLMs. You'll starve. Picking edible fruits from plants also requires precision, both in terms of the hand/eye coordination of actually picking it as well as in terms of knowing what's edible and what's poisonous.

When you fill up your coffee cup in the morning, I sure hope you aim accurately and don't pour half of it all over your desk. And don't even get me started on the process of making coffee that isn't completely unpalatable.

Re: Website streamed live directly from a model

#124

Post by Timwi » Sat, Apr 25, 2026, 1:27 AM UTC

monkpit wrote: post #64

Ah I was thinking this created the webpage itself, which I always thought was an interesting concept. Some future where the application is crafted in realtime to fulfill the needs of the user. Has anyone made something like this?

My needs as a user are for a UI to be consistent and predictable.

Good luck.

Re: Website streamed live directly from a model

#125

Post by monkpit » Sat, Apr 25, 2026, 8:49 PM UTC

Timwi wrote: post #124

monkpit wrote: post #64

Ah I was thinking this created the webpage itself, which I always thought was an interesting concept. Some future where the application is crafted in realtime to fulfill the needs of the user. Has anyone made something like this?

My needs as a user are for a UI to be consistent and predictable. Good luck.

To be fair, I didn’t say it was a _good_ idea…