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

461–470 of 762 posts

Re: Human coders are still better than LLMs

#461

Post by wvenable »

AdieuToLogic wrote: post #457
bsder wrote: post #393

Earlier quoted context omitted.

LLMs are a decent search engine a la Google circa 2005. It's been 20 years since that, so I think people have simply forgotten that a search engine can actually be useful as opposed to ad infested SEO sewage sludge. The problem is that the conversational interface, for some reason, seems to turn off the natural skepticism that people have when they use a search engine.

> LLMs are a decent search engine a la Google circa 2005. Statistical text (token) generation made from an unknown (to the user) training data set is not the same as a keyword/faceted search of arbitrary content acquired from web crawlers. > The problem is that the conversational interface, for some reason, seems to turn off the natural skepticism that people have when they use a search engine. For me, my skepticism…

I almost never bother using Google anymore. When I search for something, I'm usually looking for an answer to question. Now I can just ask the question and get the answer without all the other stuff.

I will often ask the LLM to give me web pages to look at it when I want to do further reading.

As LLMs get better, I can't see myself going back to Google as it is or even as it was.

Re: Human coders are still better than LLMs

#462

Post by wvenable »

myvoiceismypass wrote: post #439
andrekandre wrote: post #432

Earlier quoted context omitted.

> the conversational interface, for some reason, seems to turn off the natural skepticism that people have n=1 but after having chatgpt "lie" to me more than once i am very skeptical of it and always double check it, whereas something like tv or yt videos i still find myself being click-baited or grifted (iow less skeptical) much more easily still... any large studies about this would be very interesting...

I get irrationally frustrated when ChatGPT hallucinates npm packages / libraries that simply do not exist. This happens… weekly for me.

Weird. I used to have that happen when it first came out but I haven't experienced anything like that in a long time. Worst case it's out of date rather than making stuff up.

Re: Human coders are still better than LLMs

#463

Post by abletonlive »

kweingar wrote: post #287
bbarn wrote: post #220

Earlier quoted context omitted.

Honestly, if you're not doing it now, you're behind. The sheer amount of time savings using it smartly can give you to allow you to focus on the parts that actually matter is massive.

If progress continues at the rate that AI boosters expect, then soon you won't have to use them smartly to get value (all existing workflows will churn and be replaced by newer, smarter workflows within months), and everybody who is behind will immediately catch up the moment they start to use the tool.

But if it doesn't and you're not using it now then you're gonna be behind and part of the group getting laid off

the people that are good at using these tools now will be better at it later too. you might have closed the gap quite a bit but you will still be behind

using LLMs are they are now requires a certain type of mindset that takes practice to maintain and sharpen. It's just like a competitive game. The more intentionally do it, the better you get. And the meta changes every 6 months to a year.

That's why I scroll and laugh through all the comments on this thread dismissing it, because I know that the people dismissing it are the problem.

the interface is a chatbox with no instructions or guardrails. the fact that folks think that their experience is universal is hilarious. so much of using LLM right now is context management.

I can't take most of yall in this thread seriously

Re: Human coders are still better than LLMs

#464

Post by apwell23 »

lupire wrote: post #342
vidarh wrote: post #212

Earlier quoted context omitted.

> I can create a new programming language, give the definition of it in the prompt, ask it to code something in my language, and expect something out. It might even work. I literally just pointed out the same time without having seen your comment. Second this. I've done this several times, and it can handle it well. Already GPT3.5 could easily reason about hypothetical languages given a grammar or a loose description…

Second, how much of commenting is really never done before?

good question. why isn't the gp using llm to generate comments then.

Re: Human coders are still better than LLMs

#465

Post by wvenable »

bigstrat2003 wrote: post #344
smokel wrote: post #46

Earlier quoted context omitted.

Stating this without any arguments is not very convincing. Perhaps you remember that language models were completely useless at coding some years ago, and now they can do quite a lot of things, even if they are not perfect. That is progress, and that does give reason to extrapolate. Unless of course you mean something very special with "solving programming".

> Perhaps you remember that language models were completely useless at coding some years ago, and now they can do quite a lot of things, even if they are not perfect. IMO, they're still useless today, with the only progress being that they can produce a more convincing facade of usefulness. I wouldn't call that very meaningful progress.

I don't know how someone can legitimately say that they're useless. Perfect, no. But useless, also no.

Re: Human coders are still better than LLMs

#466

Post by hello_computer »

Corporations have many constraints—advertisers, investors, employees, legislators, journalists, advocacy groups. So many “white lies” are baked into these models to accommodate those constraints, nerfing the model. It is only a matter of time before hardware brings this down to the hobbyist level—without those constraints—giving the present methods their first fair fight; while for now, they are born lobotomized. Some of the “but, but, but…”s we see here daily to justify our jobs are not going to hold up to a non-lobotomized LLM.

Re: Human coders are still better than LLMs

#467

Post by drodgers »

ben-schaaf wrote: post #375
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…

Friendly reminder that people like you were saying the exact same thing about metaverse, VR, web3, crypto, etc.

Yes. If you judge only from the hype, then you can't distinguish LLMs from crypto, or Nuclear Weapons from Nuclear Automobiles.

If you always say that every new fad is just hype, then you'll even be right 99.9% of the time. But if you want to be more valuable than a rock (https://www.astralcodexten.com/p/heuristics-that-almost-alwa...), then you need to dig into the object-level facts and form an opinion.

In my opinion, AI has a much higher likelihood of changing everything very quickly than crypto or similar technologies ever did.

Re: Human coders are still better than LLMs

#468

Post by abootstrapper »

ben-schaaf wrote: post #375
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…

Friendly reminder that people like you were saying the exact same thing about metaverse, VR, web3, crypto, etc.

I didn’t buy the hype of any of those things, but I believe AI is a going to change everything much like the introduction of the internet. People are dismissing AI because its code is not bug free, completely dismissing the fact that it generates PRs in minutes from a poorly written text prompt. As if that’s not impressive. In fact if you put a human engineer on the receiving end of the same prompt with the same context as what we’re sending to the LLM, I doubt they could produce code half as good in 10x the time. It’s science fiction coming true, and it’s only going to continue to improve.

Re: Human coders are still better than LLMs

#469

Post by gessha »

bdangubic wrote: post #443
myvoiceismypass wrote: post #439

Earlier quoted context omitted.

I get irrationally frustrated when ChatGPT hallucinates npm packages / libraries that simply do not exist. This happens… weekly for me.

just ask it to write and publish them and you good :)

Jia Tan will have to work 24/7 :)

Re: Human coders are still better than LLMs

#470

Post by dingnuts »

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

I've seen very long prompts that are as long as a school essay and those didn't take ten seconds either
Post reply on HN