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

151–160 of 332 posts

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

#151

Post by amrocha »

ed wrote: post #135

Like a lot of people in this thread I prototyped something similar. One experiment just connected GPT to a socket and gave it some bindings to SQLite. With a system prompt like “you’re an http server for a twitter clone called Gwitter.” you can interact directly with the LLM from a browser. Of course it was painfully slow, quickly went off the rails, and revealed that LLM’s are bad at business logic. But something li…

There is no world where the technology that exists as we understand it leads to your techno dystopia in any way.

These models can’t even do continuous learning yet. There’s no evidence that the current tech will ever evolve beyond what it is today.

Not to mention that nobody is asking for any of this.

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

#152

Post by cluckindan »

sifar wrote: post #148
d-lisp wrote: post #96

Earlier quoted context omitted.

Maybe I should have rephrased everything with : " Make me happy" "Make me happy" "Make me happy" "Make me happy"

That's an infinite loop.

Stop the loop of wanting

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

#153

Post by anthk »

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.

Ah, sure; that's why everyone got Adblock and UBo in first place. Even more under phones.

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

#154

Post by sublinear »

OJFord wrote: post #125
113 wrote: post #57

Earlier quoted context omitted.

> Because nobody actually wants a "web app". People want food, love, sex or: solutions. Okay but when I start my car I want to drive it, not fuck it.

...so that you can get to the supermarket for food, to meet someone you love, meet someone you may or may not love, or to solve the problem of how to get to work; etc. Your ancestors didn't want horses and carts, bicycles, shoes - they wanted the solutions of the day to the same scenarios above.

As much as I love your point, this is where I must ask whether you even want a corporeal form to contain the level of ego you're describing. Would you prefer to be an eternal ghost?

To dismiss the entire universe and its hostilities towards our existence and the workarounds we invent in response as mere means to an end rather than our essence is truly wild.

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

#155

Post by anthk »

brulard wrote: post #130
d-lisp wrote: post #115

Earlier quoted context omitted.

I did that in the past, without a chatbot. Plain text search is really powerful.

Full assistant and a text search are quite a bit different things in terms of usefulness

Not for org-mode.

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

#156

Post by sixdimensional »

ares623 wrote: post #142
sixdimensional wrote: post #124

Earlier quoted context omitted.

Have you tried the thought experiment though? I agree this way seems "wrong", but try putting on your engineering hat and ask what would you change to make it right? I think that is a very interesting thread to tug on.

Running inference for every interaction seems a bit wasteful IMO, especially with a chance for things to go wrong. I’m not smart enough to come up with a way on how to optimize a repetitive operation though.

I totally agree. The reason I asked before offering any solution ideas was I was curious what you might think.

My brain went to the concept of memoization that we use to speed up function calls for common cases.

If you had a proxy that sat in front of the LLM and cached deterministic responses for inputs, with some way to maybe even give feedback when a response is satisfactory.. this could be a building block for a runtime design mode or something like that.

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

#158

Post by samdoesnothing »

cheema33 wrote: post #87
jstummbillig wrote: post #48

Earlier quoted context omitted.

Because nobody actually wants a "web app". People want food, love, sex or: solutions. You or your coworker are not a web app. You can do some of the things that web apps can, and many things that a web app can't, but neither is because of the modality. Coded determinism is hard for many problems and I find it entirely plausible that it could turn out to be the wrong approach in software, that is designed to solve som…

> Average humans are pretty great at solving a certain class of complex problems that we tried to tackle unsuccessfully with many millions lines of deterministic code.. Are you suggesting that an average user would want to precisely describe in detail what they want, every single time, instead of clicking on a link that gives them what they want?

I think they're suggesting that some problems are trivially solvable by humans but extremely hard to do with code - in fact the outcome can seem non-deterministic despite it being deterministic because there are so many confounding variables at play. This is where an LLM or other for of AI could be a valid solution.

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

#159

Post by samrolken »

Finbarr wrote: post #109

If you added a few more tools that let the LLM modify code files that would directly serve requests, that would significantly speed up future responses and also ensure consistency. Code would act like memory. A direct HTTP request to the LLM is like a cache miss. You could still have the feedback mechanism allowing a bypass that causes an update to the code. Perhaps code just becomes a store of consistency for LLMs o…

This was an unserious experiment meant to illustrate the gap and bottlenecks that are still there. I agree that there's a lot that could be done to optimize this kind of approach. But even if you did, I'm not sure the results would be viable and I'm pretty sure classic coding (with LLM assistance and all) would still outperform such a product.

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

#160

Post by atoav »

> When inference gets 10x faster, maybe the question shifts from "how do we generate better code?" to "why generate code at all?"

Because we live on a planet with finite resources and running certain problems in an LLM is probably one of the most computationally expensive ways of solving them?

Post reply on HN