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

Show HN: Why write code if the LLM can just do the thing? (web app experiment)

github.com

Post reply on HN
Print view View original

31–40 of 332 posts

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#31

Post by jeltz »

admax88qqq wrote: post #22
sunaurus wrote: post #20

The question posed sounds like "why should we have deterministic behavior if we can have non-deterministic behavior instead?" Am I wrong to think that the answer is obvious? I mean, who wants web apps to behave differently every time you interact with them?

Web apps kind of already do that with most companies shipping constant UX redesigns, A/B tests, new features, etc. For a typical user today’s software isn’t particularly deterministic. Auto updates mean your software is constantly changing under you.

And most end users hate it.

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#32

Post by Jaygles »

admax88qqq wrote: post #22
sunaurus wrote: post #20

The question posed sounds like "why should we have deterministic behavior if we can have non-deterministic behavior instead?" Am I wrong to think that the answer is obvious? I mean, who wants web apps to behave differently every time you interact with them?

Web apps kind of already do that with most companies shipping constant UX redesigns, A/B tests, new features, etc. For a typical user today’s software isn’t particularly deterministic. Auto updates mean your software is constantly changing under you.

I don't think that is what the original commenter was getting at. In your case, the company is actively choosing to make changes. Whether its for a good reason, or leads to a good outcome, is beside the point.

LLMs being inherently non-deterministic means using this technology as the foundation of your UI will mean your UI is also non-deterministic. The changes that stem from that are NOT from any active participation of the authors/providers.

This opens a can of worms where there will always be a potential for the LLM to spit out extremely undesirable changes without anyone knowing. Maybe your bank app one day doesn't let you access your money. This is a danger inherent and fundamental to LLMs.

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#33

Post by samrolken »

julianlam wrote: post #24

I can't wait to build against an API whose outputs can radically change by the second! Usually I have to wait for the company running the API to push breaking changes without warning.

As an unserious experiment, I deliberately left this undefined for max hallucinations chaos. But in practice you could easily add the schemata for stuff in the application-defining prompt. Not that I’m saying that makes this approach any more practical…

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#35

Post by ehutch79 »

thih9 wrote: post #30
sunaurus wrote: post #20

The question posed sounds like "why should we have deterministic behavior if we can have non-deterministic behavior instead?" Am I wrong to think that the answer is obvious? I mean, who wants web apps to behave differently every time you interact with them?

> who wants web apps to behave differently every time you interact with them? Technically everyone, we stopped using static pages a while ago. Imagine pages that can now show you e.g. infinitely customizable UI; or, more likely, extremely personalized ads.

No.

When I go to the dmv website to renew my license, I want it to renew my license every single time

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#37

Post by myhf »

sunaurus wrote: post #20

The question posed sounds like "why should we have deterministic behavior if we can have non-deterministic behavior instead?" Am I wrong to think that the answer is obvious? I mean, who wants web apps to behave differently every time you interact with them?

Designing a system with deterministic behavior would require the developer to think. Human-Computer Interaction experts agree that a better policy is to "Don't Make Me Think" [1]

[1] https://en.wikipedia.org/wiki/Don%27t_Make_Me_Think

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#38

Post by Konnstann »

MangoCoffee wrote: post #27

Here's why I don't get why people are badmouthing AI assist tools from Claude for Excel to Cursor to any new AI assist tool. Why not try it out, and if it doesn't work for you or creates more work for you, then ditch it. All these AI assist tools are just tools.

The problem arises when there's outside pressure to use the tools, or now you're maintaining code written by someone else through the use of the tools, where it could have been good enough for them because they don't have to deal with downstream effects. At least that's been my negative experience with AI coding assistance. You could say "just get a new job" but unfortunately that's hard.

Re: Show HN: Why write code if the LLM can just do the thing? (web app experiment)

#40

Post by admax88qqq »

Jaygles wrote: post #32
admax88qqq wrote: post #22

Earlier quoted context omitted.

Web apps kind of already do that with most companies shipping constant UX redesigns, A/B tests, new features, etc. For a typical user today’s software isn’t particularly deterministic. Auto updates mean your software is constantly changing under you.

I don't think that is what the original commenter was getting at. In your case, the company is actively choosing to make changes. Whether its for a good reason, or leads to a good outcome, is beside the point. LLMs being inherently non-deterministic means using this technology as the foundation of your UI will mean your UI is also non-deterministic. The changes that stem from that are NOT from any active participatio…

Right I get tha. The point I’m making is that from a users perspective it’s functionally very similar. A non deterministic llm or a non deterministic company full of designers and engineers.
Post reply on HN