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

Build and Host AI-Powered Apps with Claude – No Deployment Needed

anthropic.com

Post reply on HN
Print view View original

101–110 of 150 posts

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#101

Post by moron4hire »

socketcluster wrote: post #63
alach11 wrote: post #57

This is starting to encroach on Lovable, right? I do suspect the effect of these "vibe coded" apps on the SaaS market will be smaller than expected. Heavier-featured apps will have all sorts of functionality and polish a user won't even think to ask Claude to build. And the amount of effort to describe everything you need an app to do is higher than it seems. Instead, I think this is going to open a new paradigm with…

Yes and it may open the door for new platforms with pure backend (BaaS) focus. With AI hallucinations, letting AI write backend code is not feasible due to security implications. Access controls still require a control panel which can be easily audited. The frontend, however, is a completely different story. It reminds me of a saying from one of my ex-colleagues "Frontend development is like building a house of cards…

I am begging you to please discard this incredibly naive viewpoint before you get someone hurt. Please go learn more about secure development practices.

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#102

Post by cranium »

wwdx wrote: post #100
Pmop wrote: post #89

Earlier quoted context omitted.

Yep. Meanwhile I’m trying to figure out how can I make something that people would want to pay for, and how can I charge them, if they’re going to interact directly with Claude and burn their own quota.

anthro needs to let the creator charge % on top of their usage quota or give points/money to the creator to fix up the incentives here

That's a really good idea! That would handle micropayments that nobody would even bother with (to pay, to process, to receive, ...).

Could even have users select the payment %age or have it set by the contract tier between the app creator and the user (10% for simple user, 20% for pro access with other features, 40% enterprise,...).

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#103

Post by revskill »

WXLCKNO wrote: post #2

The tiniest step towards a future where AI eats all apps. No persistent storage and other limitations make it just a toy for now but we can imagine how people will just create their own Todo apps, gym logging apps and whatever other simple thing. no external API access currently but when that's available or app users can communicate with other app users, some virality is possible for people who make the best tiny app…

Human being is funny. They should just sit at home and doing nothing instead.

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#104

Post by yahoozoo »

falcor84 wrote: post #38
SonomaSays wrote: post #24

Earlier quoted context omitted.

There is coming a very_soon_time whereby one will have to ensure all the routes and failure_modes for the AIs plumbing are functional. What if the outage is specifically that AI_agent cant reach [thing]?

> What if the outage is specifically that AI_agent cant reach [thing]? We already saw some examples of this in Anthropic's safety papers - the AI will reach out to the human to get help with that - essentially using a human as an API/tool.

Or it will contact the FBI

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#105

Post by DonHopkins »

kookamamie wrote: post #93
cube00 wrote: post #72

Earlier quoted context omitted.

Thanks for extracting this. I always enjoy examples of prompt artists thinking they can beg their way of the LLM's janky behaviour. > Critical UI Requirements > Therefore, you SHOULD ALWAYS test your completion requests first in the analysis tool before building an artifact. > To reiterate: ALWAYS TEST AND DEBUG YOUR PROMPTS AND ORCHESTRATION LOGIC IN THE ANALYSIS TOOL BEFORE BUILDING AN ARTIFACT THAT USES window.cla…

Maybe if we added ALWAYS BE RIGHT NEVER BE WRONG it will work this time?

The problem is that each LLM behaves totally differently in response to the exact same prompts. You can't just tell them all to be RIGHT and expect the same or even correct results everywhere everytime.

For example, Grok will interpret "BE RIGHT" as an imperative command to inject White Supremacist Ideology and Holocaust Denial into dialogs about quantum physics and children's bedtime stories.

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#108

Post by amelius »

owebmaster wrote: post #107
amelius wrote: post #106

Remember, folks: don't build your castle in someone else's kingdom.

That's not a great advice, actually. Don't build just one castle and extract all value from the kingdom to your castles outside of it.

That's ... a lot of work. If you have that kind of resources you might as well play an entirely different game.

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#109

Post by Workaccount2 »

headcanon wrote: post #16
WXLCKNO wrote: post #2

The tiniest step towards a future where AI eats all apps. No persistent storage and other limitations make it just a toy for now but we can imagine how people will just create their own Todo apps, gym logging apps and whatever other simple thing. no external API access currently but when that's available or app users can communicate with other app users, some virality is possible for people who make the best tiny app…

One thing I've learned is that no matter how easy it is to create stuff, most users will still favor the one-click app install, even if they don't get full control over the workflow. With that said, I'm sure there are a lot of power users who are loving the lower barrier to creation

A huge difference between bespoke generated AI apps and one click download apps is that the friction drops dramatically.

Downloading the app may be one click...but then create an account. Attach a CC. Follow a tutorial. Figure out the app even more.

With LLM apps, there is none of that. You created the app so you pretty much know a priori how to use it. If you are unsure the model knows and you can just ask. If you want it to do something different, the model can just change it for you.

The modern software paradigm is building software that covers as massive of a solution space as possible, so as many users as possible have a problem that is covered by that space. You end up having to make lots of compromises and unintuitive steps to cover all the bases.

LLM apps cover your problem space pretty much perfectly, without anything more.

Re: Build and Host AI-Powered Apps with Claude – No Deployment Needed

#110

Post by bethekidyouwant »

DonHopkins wrote: post #105
kookamamie wrote: post #93

Earlier quoted context omitted.

Maybe if we added ALWAYS BE RIGHT NEVER BE WRONG it will work this time?

The problem is that each LLM behaves totally differently in response to the exact same prompts. You can't just tell them all to be RIGHT and expect the same or even correct results everywhere everytime. For example, Grok will interpret "BE RIGHT" as an imperative command to inject White Supremacist Ideology and Holocaust Denial into dialogs about quantum physics and children's bedtime stories.

here we have a glowing example of humans not injecting their baggage into every conversation
Post reply on HN