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

291–300 of 332 posts

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

#291

Post by array_key_first »

an_guy wrote: post #281
array_key_first wrote: post #188

Earlier quoted context omitted.

Well, software has been known to have vulnerabilities... Consider this: the bank teller is non-deterministic, too. They could give you 500 dollars of someone else's money. But they don't, generally.

Bank tellers are deterministic though. They have a set protocol for each cases and escalate unknown cases to a more deterministic point of contact. It will be difficult to incorporate relative access or restrictions to features with respect to users current/known state or actions. Might as well write the entire web app at that point.

I think the bank teller's systems and processes are deterministic, but the teller itself is not. They could even rob the bank, if they wanted to. They could shoot the customers. They don't, generally, but they can.

I think, if we can efficiently capture a way to "make" LLMs conform to a set of processes, you can cut out the app and just let the LLM do it. I don't think this makes any sense for maybe the next decade, but perhaps at some point it will. And, in such time, software engineering will no longer exist.

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

#292

Post by ethmarks »

runarberg wrote: post #287
ethmarks wrote: post #257

Earlier quoted context omitted.

That's a great point, and I think I was being vague before. To clarify, I was making a broad statement about automation in general. Running an automated loom is more efficient in every way that getting humans to weave cloth by hand. For most tasks, automation is more efficient. However, there are tasks that humans can still do more efficiently than our current engines of automation. Go is a good example because human…

I‘m not convinced this exercise in what to and what not to include in this cost-benefit-analysis will lead to anything. We can always arbitrarily include an extra item to include to shift the calculations in our favor. For example I could simply add the cost of creating the data which is fed into the training set of an LLM, that creation is done by our human biological machinery and hence has the cost of the frozen b…

You've convinced me. I did not consider the human cost of producing training data, I did not consider whether or not LLMs were actually saving effort, and I did not consider the extra effort to verify LLM output. I have nothing more to add other than to thank you for taking the time to write such a persuasive and high-quality reply. The internet would be a better place if there were more people like you on it. Thank you for making me less wrong.

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

#293

Post by anon291 »

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?

Llms are easily made deterministic by choosing the selection strategy. More than being deterministic they are also fully analayzable and you don't run into issues like the halting problem if you constrain the output appropriately.

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

#294

Post by awesomecomment »

shswkna wrote: post #254
tags2k wrote: post #252

Earlier quoted context omitted.

Most of us actually want to get somewhere to do an activity to then have known we did it for the rest of our lives as if to extract some intangible pleasure from its memory. Why don't we just hallucinate that we did it?

This leads to us asking the deepest question of all: What is the point of our existence. Or as someone suggests lower down, in our current form all needs could ultimately be satisfied if AI just provided us with the right chemicals. (Which drug addicts already understand) This can be answered though, albeit imperfectly. On a more reductionist level, we are the cosmos experiencing itself. Now there are many ways to ap…

[dead]

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

#295

Post by fouc »

bloomca wrote: post #233
AmbroseBierce wrote: post #82

Earlier quoted context omitted.

>Can you set some timers for my sport session, can you plan a pure body weight session ? Yes, that's perfect. Wait, actually, remove the jumping jacks." Better yet, why exercise -which is so repetitive- if we can create a machine that just does it for you, including the dopamine triggering, why play an arcade video game where we can create a machine that fires the neuron needed to produce the exact same level of a ex…

> Bleak, we are oversimplifying existence itself and it doesn't lead to a nice place. We are already on this path for many-many years, certainly decades if not centuries, although availability was definitely spotty in the past. It is also kind of impossible to hop off this train, while it is individually possible to reject any of these conveniences, in general they just become a part of life. Which is not necessarily…

> although availability was definitely spotty in the past.

lol, that seems like a reference to the William Gibson quote "The future is already here, it's just unevenly distributed"

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

#298

Post by kennywinker »

jstummbillig wrote: post #69
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.

Most of us actually drive a car to get somewhere. The car, and the driving, are just a modality. Which is the point.

If this was a good answer to mobility, people would prefer the bus over their car. It’s non-deterministic - when will it come? How quick will i get there? Will i get to sit? And it’s operated by an intelligent agent (driver).

Every reason people prefer a car or bike over the bus is a reason non-deterministic agents are a bad interface.

And that analogy works as a glimpse into the future - we’re looking at a fast approaching world where LLMs are the interface to everything for most of us - except for the wealthy, who have access to more deterministic services or actual human agents. How long before the rich person car rental service is the only one with staff at the desk, and the cheaper options are all LLM based agents? Poor people ride the bus, rich people get to drive.

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

#299

Post by keeda »

runarberg wrote: post #199
ethmarks wrote: post #169

Earlier quoted context omitted.

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…

I suspect you may be either underestimating how efficient our brains are at computing or severely underestimating how much energy these AI models take to train and run. Even including our system of comfort like refrigerated blueberries in January and AC cooling a 40° C heat down to 25° C (but excluding car commutes, because please work from home or take public transit) the human is still far far more energy efficient…

Wait hold on, let's put some numbers on this. Please correct my calculations if I'm wrong.

1. The human brain draws 12 - 20 watts [1, 2]. So, taking the lower end, a task taking one hour of our time costs 12 Wh.

2. An average ChatGPT query is between 0.34 Wh - 3 Wh. A long input query (10K tokens) can go up to 10 Wh. [3] I get the best results by carefully curating the context to be very tight, so optimal usage would be in the average range.

3. I have had cases where a single prompt has saved me at least an hour of work (e.g. https://news.ycombinator.com/item?id=44892576). Let's be pessimistic and say it takes 3 prompts at 3 Wh (9 Wh) and 10 minutes (2 Wh) of my time prompting and reviewing to complete a task. That is 11 Wh for the same task, which still beats out the human brain unassisted!

And that's leaving aside the recent case where I vibecoded and deployed a fully-tested endpoint on a cloud platform I had no prior experience in, over the course of 2 - 3 hours. I estimate it would have taken me a whole day just to catch up on the documentation and another 2 days tinkering with the tools, commands and code. That's at least an 8x power savings assuming an 8-hour workday!!

4. But let's talk data instead of anecdotes. If you do a wide search, there is a ton of empirical evidence that improves programmer productivity by 5 - 30% (with a lot of nuance). I've cited some here: https://news.ycombinator.com/item?id=45379452 -- there is no measure of the amount of prompt usage to estimate energy usage, but those are significant productivity boosts.

Even the METR study that appeared to show AI coding lowering productivity also showed that AI usage broadly increased in idle-time in users. That is, calendar time for task completion may have gone up, but that included a lot of idle time where people were doing no cognitive work at all. Someone should run the numbers, but maybe it resulted in lower power consumption!

---

But what about the training costs? Sure we've burned gazillions of GWh on training already, and the usual counterpoint is "what about the cost involved in evolution?" but let's assume we stopped training all models today. They will still serve all future prompts at the same power consumption rates discussed above.

However every new human will take 15 - 20 years of education to get to be a novice in a single domain, followed by many more years of experience to become proficient. We're comparing apples and blueberries here, but that's a LOT of energy to even start becoming productive, but a trained LLM is instantly productive in multiple domains forever.

My hunch is that if we do a critical analysis of amortized energy consumption, LLMs will probably beat out humans. If not already, soon with the rate of token costs plummeting all the time.

[1] https://psychology.stackexchange.com/questions/12385/how-muc...

[2] https://press.princeton.edu/ideas/is-the-human-brain-a-biolo...

[3] https://epoch.ai/gradient-updates/how-much-energy-does-chatg...

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

#300

Post by tomcam »

latexr wrote: post #256
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…

> Because nobody actually wants a "web app". People want food, love, sex or: solutions. Talk about a nonsensical non-sequitur, but I’ll bite. People want those to be deterministic too, to a large extent. When people cook a meal with the same ingredients and the same times and processes (like parameters to a function), they expect it to taste about the same, they never expect to cook a pizza and take a salad out of th…

> When they have sex, people expect to ejaculate and feel good, not have their intercourse morph into a drag race with a clown half-way though.

speak for yourself

Post reply on HN