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

Human coders are still better than LLMs

antirez.com

Post reply on HN
Print view View original

501–510 of 762 posts

Re: Human coders are still better than LLMs

#501

Post by abletonlive »

kweingar wrote: post #498
abletonlive wrote: post #491

Earlier quoted context omitted.

> If the "meta" changes so quickly, then that sets an upper bound as to how far behind you are, no? No, the top players when the meta changes in competitive games remain the top players. They also figure out the new meta faster than the casual players.

This is why devs who started with J2ME are the holy grail of app developers, since they started making apps years before iPhone devs

you sound mad you could be spending this time upskilling instead.

but i'll say it again, when the meta changes the people that were at the top will quickly find themselves at the top again.

listen, the reason why they were in the top in the first place and you aren't is a mindset thing. the top are the curious that are experimenting and refining, sharing with each other techniques developed over time.

the complacent just sit around and lets the world happen to them. they, like you are expressing now, think that when the meta switches the bottom will suddenly find themselves at the top and the top will have nothing.

look around you, that's obviously not how the world works.

but yes, laughing

Re: Human coders are still better than LLMs

#502

Post by chii »

eikenberry wrote: post #320
garciasn wrote: post #223

Earlier quoted context omitted.

This is the response to most new technologies; folks simply don't want to accept the future before the ramifications truly hit. If technology folk cannot see the INCREDIBLE LEAP FORWARD made by LLMs since ChatGPT came on the market, they're not seeing the forest through the trees because their heads are buried in the sand. LLMs for coding are not even close to imperfect, yet, but the saturation curves are not flatten…

I don't think it is only (or even mostly) not wanting to accept it, I think it is at least equal measure just plain skepticism. We've seen all sorts of wild statements about how much something is going to revolutionize X and then turns out to be nothing. Most people disbelieve these sorts of claims until they see real evidence for themselves... and that is a good default position.

hedging the possibility that they get displaced economically before it happens is always prudent.

If the future didnt turn out to be revolutionary, you now have done some "unnecessary" work at worst, but might've acquired some skills or value at least. In the case of most well off programmers, i suspect buying assets/investments which can afford them at least a reasonable lifestyle is likely too.

So the default position of being stationary, and assuming the world continues the way it has been, is not such a good idea. One should always assume the worst possible outcome, and plan for that.

Re: Human coders are still better than LLMs

#503

Post by pixl97 »

na4ma4 wrote: post #357
tharkun__ wrote: post #332

Earlier quoted context omitted.

Fair enough on 'cutting the learning tree' at some points i.e. ignoring that you don't understand yet why something works/does what it does. We (should) keep doing that later on in life as well. But unless you teach a kid that's never done any math where `x` was a thing to program, what's so hard about understanding the concept of a variable in programming?

I think they're just using hyperbole for the watershed moment when you start to understand your first programming language. At first it's all mystical nonsense that does something, then you start to poke at it and the response changes, then you start adding in extra steps and they do things, you could probably describe it as more of a Eureka! moment. At some point you "learn variables" and it's hard to imagine being…

Yep, I remember way back when in grade school messing around with the gorillas.bas file with nearly zero understanding. You could change stuff in one place and it would change the gravity in the game. Changing something else and the game might not run. Change some other lines and it totally freaks out.

I didn't have any programming books or even the internet back then. It was a poke and prod at the magical incantations type of thing.

Re: Human coders are still better than LLMs

#504

Post by Zamaamiro »

AndrewKemendo wrote: post #448
GiorgioG wrote: post #403

Earlier quoted context omitted.

So what you’re saying is you need to be very specific and detailed when writing your specifications for the LLM to spit out the code you want. Sounds like I can just skip the middle man and code it myself.

Not in 10 seconds

You probably didn’t write up a detailed prompt with perfect specifications in 10 seconds, either.

In my experience, it doesn’t matter how good or detailed the prompt is—after enough lines of code, the LLM starts making design decisions for you.

This is why I don’t accept LLM completions for anything that isn’t short enough to quickly verify that it is implemented exactly as I would have myself. Usually, that’s boilerplate code.

Re: Human coders are still better than LLMs

#505

Post by chii »

kccqzy wrote: post #21
wanderingstan wrote: post #7

“Better” is always task-dependent. LLMs are already far better than me (and most devs I’d imagine) at rote things like getting CSS syntax right for a desired effect, or remembering the right way to invoke a popular library (e.g. fetch) These little side quests used to eat a lot of my time and I’m happy to have a tool that can do these almost instantly.

> and most devs I’d imagine What an awful imagination. Yes there are people who don't like CSS but are forced to use it by their job so they don't learn it properly, and that's why they think CSS is rote memorization. But overall I agree with you that if a company is too cheap to hire a person who is actually skilled at CSS, it is still better to hoist that CSS job onto LLMs than an unwilling human. Because that unwi…

The LLM outputs good enough CSS, but is (way) cheaper than someone who's actually good at CSS.

Re: Human coders are still better than LLMs

#506

Post by chii »

JackSlateur wrote: post #194
acquisitionsilk wrote: post #192

It is quite heartening to see so many people care about "good code". I fear it will make no difference. The problem is that the software world got eaten up by the business world many years ago. I'm not sure at what point exactly, or if the writing was already on the wall when Bill Gates' wrote his open letter to hobbyists in 1976. The question is whether shareholders and managers will accept less good code. I don't s…

Code is meant to power your business Bad code leads to bad business This makes me think of hosting departement; You know, which people who are using vmware, physical firewalls, dpi proxies and whatnot; On the other edge, you have public cloud providers, which are using qemu, netfilter, dumb networking devices and stuff Who got eaten by whom, nobody could have guessed ..

> Bad code leads to bad business

Bad business leads to bad business.

Bad code might be bad, or might be sufficient. It's situational. And by looking at what exists today, majority of code is pretty bad already - and not all businesses with bad code lead to bad businesses.

In fact, some bad code are very profitable for some businesses (ask any SAP integrator).

Re: Human coders are still better than LLMs

#507

Post by benstein »

ChrisMarshallNY wrote: post #433

Really good coders (like him) are better. Mediocre ones … maybe not so much. When I worked for a Japanese optical company, we had a Japanese engineer, who was a whiz. I remember him coming over from Japan, and fixing some really hairy communication bus issues. He actually quit the company, a bit after that, at a very young age, and was hired back as a contractor; which was unheard of, in those days. He was still work…

+1000. "Human coders are still better than LLMs" is a hot take. "Antirez is still better than LLMs" is axiomatic ;-)

Re: Human coders are still better than LLMs

#508

Post by mullingitover »

Jolter wrote: post #132
bgwalter wrote: post #114

Earlier quoted context omitted.

Yet you are working on your own replacement, while your colleagues are taking the prudent approach.

Here’s the deal: if you won’t write your replacement, a competitor will do it and outprice your employer. Either way you’re out of a job. May be more prudent to adapt to the new tools and master them rather than be left behind? Do you want to be a jobless weaver, or an engineer building mechanical looms for a higher pay than the weaver got?

> Either way you’re out of a job.

Tools and systems which increase productivity famously always put everyone out of a job, which is why after a couple centuries of industrial revolution we're all unemployed.

Re: Human coders are still better than LLMs

#509

Post by kuahyeow »

Jolter wrote: post #132
bgwalter wrote: post #114

Earlier quoted context omitted.

Yet you are working on your own replacement, while your colleagues are taking the prudent approach.

Here’s the deal: if you won’t write your replacement, a competitor will do it and outprice your employer. Either way you’re out of a job. May be more prudent to adapt to the new tools and master them rather than be left behind? Do you want to be a jobless weaver, or an engineer building mechanical looms for a higher pay than the weaver got?

Compiler is the more apt analogy to a mechanical loom.

An LLM is more like outsourcing to a consultancy. Results may vary.

Re: Human coders are still better than LLMs

#510

Post by gpm »

therealpygon wrote: post #399
Buttons840 wrote: post #379

Earlier quoted context omitted.

LLMs aren't my rubber duck, they're my wrong answer. You know that saying that the best way to get an answer online is to post a wrong answer? That's what LLMs do for me. I ask the LLM to do something simple but tedious, and then it does it spectacularly wrong, then I get pissed off enough that I have the rage-induced energy to do it myself.

LLMs follow instructions. Garbage in = garbage out generally. When attention is managed and a problem is well defined and necessary materials are available to it, they can perform rather well. On the other hand, I find a lot of the loosely-goosey vibe coding approach to be useless and gives a lot of false impressions about how useful LLMs can be, both too positive and too negative.

This hasn't been my experience (using the latest claude and gemini models). They'll produce poor code even when given a well defined easily achievable task with specific instructions. The code will usually more or less work with today's models, but it will do things like call a function to recreate a value that is already stored in a local variable... (and worse issues prop us the more design-work you leave to the LLM, even dead simple design work with really only one good answer)

I've definitely also found that the poor code can sometimes be a nice starting place. One thing I think it does for me is make me fix it up until it's actually good, instead of write the first thing that comes to mind and declare it good enough (after all my poorly written first draft is of course perfect). In contrast to the usual view of AI assisted coding, I think this style of programming for tedious tasks makes me "less productive" (I take longer) but produces better code.

Post reply on HN