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

31–40 of 762 posts

Re: Human coders are still better than LLMs

#31

Post by jaccola »

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.

I've found LLMs particularly bad for anything beyond basic styling since the effects can be quite hard to describe and/or don't have a universal description.

Also, there are often times multiple ways to achieve a certain style and they all work fine until you want a particular tweak, in which case only one will work and the LLM usually gets stuck in one of the ones that does not work.

Re: Human coders are still better than LLMs

#32

Post by ldjkfkdsjnv »

ehutch79 wrote: post #24
decasia wrote: post #10

We aren't expecting LLMs to come up with incredibly creative software designs right now, we are expecting them to execute conventional best practices based on common patterns. So it makes sense to me that it would not excel at the task that it was given here. The whole thing seems like a pretty good example of collaboration between human and LLM tools.

Uh, no. I've seen the twitter posts saying llms will replace me. I've watched the youtube videos saying llms will code whole apps on one prompt, but are light on details or only show the most basic todo app from every tutorial. We're being told that llms are now reasoning, which implies they can make logical leaps and employ creativity to solve problems. The hype cycle is real and setting expectations that get higher…

you will almost certainly be replaced by an llm in the next few years

Re: Human coders are still better than LLMs

#33

Post by marcosdumay »

mattnewton wrote: post #5

This matches my experience. I actually think a fair amount of value from LLM assistants to me is having a reasonably intelligent rubber duck to talk to. Now the duck can occasionally disagree and sometimes even refine. https://en.m.wikipedia.org/wiki/Rubber_duck_debugging I think the big question everyone wants to skip right to and past this conversation is, will this continue to be true 2 years from now? I don’t kno…

LLMs will still be this way 10 years from now.

But IDK if somebody won't create something new that gets better. But there is no reason at all to extrapolate our current AIs into something that solves programing. Whatever constraints that new thing will have will be completely unrelated to the current ones.

Re: Human coders are still better than LLMs

#34

Post by darkport »

I think this is true for deeply complex problems, but For everyday tasks an LLM is infinitely “better”.

And by better, I don’t mean in terms of code quality because ultimately that doesn’t matter for shipping code/products, as long as it works.

What does matter is speed. And an LLM speeds me up at least 10x.

Re: Human coders are still better than LLMs

#35

Post by vjvjvjvjghv »

I think we need to accept that in the not too far future LLMs will be able to do most of the mundane tasks we have to do every day. I don't see why an AI can't set up kubernetes, caching layers, testing, databases, scaling, check for security problems and so on. These things aren't easy but I think they are still very repetitive and therefore can be automated.

There will always be a place for really good devs but for average people (most of us are average) I think there will be less and less of a place.

Re: Human coders are still better than LLMs

#38

Post by bgwalter »

ehutch79 wrote: post #24
decasia wrote: post #10

We aren't expecting LLMs to come up with incredibly creative software designs right now, we are expecting them to execute conventional best practices based on common patterns. So it makes sense to me that it would not excel at the task that it was given here. The whole thing seems like a pretty good example of collaboration between human and LLM tools.

Uh, no. I've seen the twitter posts saying llms will replace me. I've watched the youtube videos saying llms will code whole apps on one prompt, but are light on details or only show the most basic todo app from every tutorial. We're being told that llms are now reasoning, which implies they can make logical leaps and employ creativity to solve problems. The hype cycle is real and setting expectations that get higher…

After the use-after-free hype article I tried CoPilot and it outright refused to find vulnerabilities.

Whenever I try some claim, it does not work. Yes, I know, o3 != CoPilot but I don't have $120 and 100 prompts to spend on making a point.

Re: Human coders are still better than LLMs

#39

Post by ljlolel »

burningion wrote: post #9

I agree, but I also didn’t create redis! It’s a tough bar if LLMs have to be post antirez level intelligence :)

Seriously, he’s one of the best on the planet of course it’s not better than him. If so we’d be cooked.

99% of professional software developers don’t understand what he said much less can come up with it (or evaluate it like Gemini).

This feels a bit like a humblebrag about how well he can discuss with an LLM compared to others vibecoding.

Re: Human coders are still better than LLMs

#40

Post by jaccola »

pupppet wrote: post #23

If an LLM just finds patterns, is it even possible for an LLM to be GOOD at anything? Doesn't that mean at best it will be average?

Most people (average and below average) can tell when something is above average, even if they cannot create above average work, so using RLHF it should be quite possible to achieve above average.

Indeed it is likely already the case that in training the top links scraped or most popular videos are weighted higher, these are likely to be better than average.

Post reply on HN