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

301–310 of 332 posts

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

#301

Post by iliaxj »

chii wrote: post #228
113 wrote: post #174

Earlier quoted context omitted.

Yeah but in this case your car is non-deterministic so

> your car is non-deterministic it's not as far as your experience goes - you press pedal, it accelerates. You turn the steering, it goes the way it turns. What the car does is deterministic. More importantly, it does this every time, and the amount of turning (or accelerating) is the same today as it was yesterday. If an LLM interpreted those inputs, can you say with confidence, that you will accelerate in a way tha…

Sometimes it doesn't though. Sometimes the engine seizes because a piece of tubing broke and you left your coolant down the road two turns ago. Or you steer off a cliff because there was coolant on the road for some reason. Or the meat sack in front of the wheel just didn't get enough sleep and your response time is degraded and you just can't quite get the thing to feel how you usually do. Ultimately the failure rate is low enough to trust your life on it, but that's just a matter of degree.

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

#302

Post by SecretDreams »

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?

Why do good thing consistently when we can do great thing that only works sometimes??? :(

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

#303

Post by pepoluan »

jstummbillig wrote: post #48
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?

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…

The issue with not having something deterministic is that when there's regression, you cannot surgically fix the regression. Because you can't know how "Plan A" got morphed into "Modules B, C, D, E, F, G," and so on.

And don't even try to claim there won't ever be any regression: Current LLM-based A.I. will 'happily' lie to you that they passed all tests -- because based on interactions in the past, it has.

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

#304

Post by pepoluan »

iliaxj wrote: post #301
chii wrote: post #228

Earlier quoted context omitted.

> your car is non-deterministic it's not as far as your experience goes - you press pedal, it accelerates. You turn the steering, it goes the way it turns. What the car does is deterministic. More importantly, it does this every time, and the amount of turning (or accelerating) is the same today as it was yesterday. If an LLM interpreted those inputs, can you say with confidence, that you will accelerate in a way tha…

Sometimes it doesn't though. Sometimes the engine seizes because a piece of tubing broke and you left your coolant down the road two turns ago. Or you steer off a cliff because there was coolant on the road for some reason. Or the meat sack in front of the wheel just didn't get enough sleep and your response time is degraded and you just can't quite get the thing to feel how you usually do. Ultimately the failure rat…

The situations you described reflects a System that has changed. And if the System has changed, then a change in output is to be expected.

It's the same as having a function called "factorial" but you change the multiplication operation to addition instead.

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

#305

Post by pepoluan »

reissbaker wrote: post #132
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?

I think it's actually conceptually pretty different. LLMs today are usually constrained to: 1. Outputting text (or, sometimes, images). 2. No long term storage except, rarely, closed-source "memory" implementations that just paste stuff into context without much user or LLM control. This is a really neat glimpse of a future where LLMs can have much richer output and storage. I don't think this is interesting because…

Or, maybe, just not use LLMs?

LLM is just one model used in A.I. It's not a panacea.

For generating deterministic output, probably a combination of Neural Networks and Genetic Programming will be better. And probably also much more efficient, energy-wise.

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

#306

Post by crabmusket »

krapp wrote: post #227
crabmusket wrote: post #114

Earlier quoted context omitted.

As experiments like TFA become more common, the argument will shift to whether anybody should think about anything at all.

What argument? I see a business model here, not an argument.

I meant "the discourse", "the conversation we are all having", interpreting the experiment in TFA as an entry in that discourse.

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

#307

Post by pepoluan »

roncesvalles wrote: post #218
finnborge wrote: post #66

Earlier quoted context omitted.

I think this is well illustrated in a lot of science fiction. Irregular or abstract tasks are fairly efficiently articulated in speech, just like the ones you provided. Simpler, repetitive ones are not. Imagine having to ask your shower to turn itself on? Or your doors to open? Contextualized to "web-apps," as you have; navigating a list maybe requires an interface. It would be fairly tedious to differentiate between…

On a tangent but I still don't know why we don't have showers where you just press a button and it delivers water at the correct temperature. It seems like the simplest thing that everyone wants. A company that manufactures and installs this (a la SolarCity) should be an instant unicorn.

What's "correct" for you might not be "correct" for others. Furthermore, your owb definition of "correct" changes depending on circumstances; sometimes you want it hotter, sometimes you want it colder. Sometimes you want to change it partway through.

How do you calculate for that?

Back in the 90s, Fuzzy Logic was thought to be the solution. In a way, yes, but only for niche/specialized purposes, and they still have to limit the variables being evaluated.

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

#308

Post by pepoluan »

lazide wrote: post #242
roncesvalles wrote: post #218

Earlier quoted context omitted.

On a tangent but I still don't know why we don't have showers where you just press a button and it delivers water at the correct temperature. It seems like the simplest thing that everyone wants. A company that manufactures and installs this (a la SolarCity) should be an instant unicorn.

Water + electronics/power typically isn’t very durable, or reliable. Most people want their shower valves to work at least 20 years, ideally 50-100.

Can be mitigated to a degree by separating the (cheaper) sensors and the (pricier) logic.

But then it will become a tradeoff of complexity vs longevity.

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

#309

Post by pepoluan »

ethmarks wrote: post #169
sramam wrote: post #104

Earlier quoted context omitted.

I work in enterprise IT and sometimes wonder if we should add the equivalent energy calculations of human effort - both productive and unproductive - that underlies these "output/cost" comparisons. I realize it sounds inhuman, but so is working in enterprise IT! :)

I agree wholeheartedly. It irks me when people critique automation because it uses large amounts of resources. Running a machine or a computer almost always uses far less resources than a human would to do the same task, so long as you consider the entire resource consumptions. Growing the food that a human eats, running the air conditioning for their home, powering their lights, fueling their car, charging their pho…

Not ALL automation can be more efficient.

Just ask Elon about his efforts to fully automate Tesla production.

Same as A.I. Current LLM-based A.I.s are not at all as efficient as a human brain.

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

#310

Post by chii »

iliaxj wrote: post #301
chii wrote: post #228

Earlier quoted context omitted.

> your car is non-deterministic it's not as far as your experience goes - you press pedal, it accelerates. You turn the steering, it goes the way it turns. What the car does is deterministic. More importantly, it does this every time, and the amount of turning (or accelerating) is the same today as it was yesterday. If an LLM interpreted those inputs, can you say with confidence, that you will accelerate in a way tha…

Sometimes it doesn't though. Sometimes the engine seizes because a piece of tubing broke and you left your coolant down the road two turns ago. Or you steer off a cliff because there was coolant on the road for some reason. Or the meat sack in front of the wheel just didn't get enough sleep and your response time is degraded and you just can't quite get the thing to feel how you usually do. Ultimately the failure rat…

all of those situations are the "driver's own fault", because they could've had a check to ensure none of that happened before driving. Not true with an LLM (at least, not as of today).
Post reply on HN