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

211–220 of 762 posts

Re: Human coders are still better than LLMs

#211

Post by UncleOxidant »

cushychicken wrote: post #153
UncleOxidant wrote: post #71

There's some whistling past the graveyard in these comments. "You still need humans for the social element...", "LLMs are bad at debugging", "LLMs lead you astray". And yeah, there's lots of truth in those assertions, but since I started playing with LLMs to generate code a couple of years ago they've made huge strides. I suspect that over the next couple of years the improvements won't be quite as large (Pareto Prin…

ChatGPT-4o is scary good at writing VHDL. Using it to prototype some low level controllers today, as a matter of fact!

Claude and Gemini are decent at it as well. I was surprised when I asked claude (and this was several months back) to come up with a testbench for some very old, poorly documented verilog. It did a very decent job for a first-cut testbench. It even collected common, recurring code into verilog tasks (functions) which really surprised me at the time.

Re: Human coders are still better than LLMs

#212

Post by vidarh »

Epa095 wrote: post #94
marcosdumay wrote: post #65

Earlier quoted context omitted.

Why state the same arguments everybody has been repeating for ages? LLMs can only give you code that somebody has wrote before. This is inherent. This is useful for a bunch of stuff, but that bunch won't change if OpenAI decides to spend the GDP of Germany training one instead of Costa Rica.

First, how much of coding is really never done before? And secondly, what you say are false (at least if taken literally). 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 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.

I find it absolutely bizarre that people still hold on to this notion that these languages can't do anything new, because it feels implausible that they have tried given how well it works.

Re: Human coders are still better than LLMs

#213

Post by koonsolo »

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…

It seems to me we're at the flat side of the curve again. I haven't seen much real progress in the last year.

It's ignorant to think machines will not catch up to our intelligence at some point, but for now, it's clearly not.

I think there needs to be some kind of revolutionary breakthrough again to reach the next stage.

If I were to guess, it needs to be in the learning/back propagation stage. LLM's are very rigid, and once they go wrong, you can't really get them out of it. A junior develop for example could gain a new insight. LLM's, not so much.

Re: Human coders are still better than LLMs

#214

Post by vidarh »

apwell23 wrote: post #123
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 no i don't remember that. They are doing similar things now that they did 3 yrs ago. They were still a decent rubber duck 3 yrs ago.

And 6 years ago GPT2 had just been released. You're being obtuse by interpreting "some years" as specifically 3.

Re: Human coders are still better than LLMs

#215

Post by bbarn »

yua_mikami wrote: post #42

The thing everyone forgets when talking about LLMs replacing coders is that there is much more to software engineering than writing code, in fact that's probably one of the smaller aspects of the job. One major aspect of software engineering is social, requirements analysis and figuring out what the customer actually wants, they often don't know. If a human engineer struggles to figure out what a customer wants and a…

The thing is, it is replacing _coders_ in a way. There are millions of people who do (or did) the work that LLMs excel at. Coders who are given a ticket that says "Write this API taking this input and giving this output" who are so far down the chain they don't even get involved in things like requirements analysis, or even interact with customers.

Software engineering, is a different thing, and I agree you're right (for now at least) about that, but don't underestimate the sheer amount of brainless coders out there.

Re: Human coders are still better than LLMs

#216

Post by jajko »

Bukhmanizer wrote: post #97
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…

There are a couple people I work with who clearly don’t have a good understanding of software engineering. They aren’t bad to work with and are in fact great at collaborating and documenting their work, but don’t seem to have the ability to really trace through code and logically understand how it works. Before LLMs it was mostly fine because they just didn’t do that kind of work. But now it’s like a very subtle chao…

Sounds almost like you definitely shouldnt use llms nor those juniors for such an important work.

Is it just me or are we heading into a period of explosion of software done, but also a massive drop of its quality? Not uniformly, just a bit of chaotic spread

Re: Human coders are still better than LLMs

#217

Post by overfeed »

seadan83 wrote: post #188
gerad wrote: post #52

Earlier quoted context omitted.

It's like chess. Humans are better for now, they won't be forever, but humans plus software is going to better than either alone for a long time.

> It's like chess. Humans are better for now, they won't be forever This is not an obviously true statement. There needs to be proof that there are no limiting factors that are computationally impossible to overcome. It's like watching a growing child, grow from 3 feet to 4 feet, and then saying "soon, this child will be the tallest person alive."

One of my favourite XKCD comics is about extrapolation https://xkcd.com/605/

Re: Human coders are still better than LLMs

#218

Post by hatefulmoron »

bluefirebrand wrote: post #146
hatefulmoron wrote: post #113

Earlier quoted context omitted.

> my point is that I think after driving a tractor for a while, the kid would really struggle to go hoe by hand like he used to, if he ever needed to That's true in the short term, but let's be real, tilling soil isn't likely to become a lost art. I mean, we use big machines right now but here we are talking about using a hoe. If you remove the context of LLMs from the discussion, it reads like you're arguing that te…

> If you remove the context of LLMs from the discussion, it reads like you're arguing that technological progress in general is bad because people would eventually struggle to live without it. I'm arguing that there are always tradeoffs and we often do not fully understand the tradeoffs we are making or the consequences of those tradeoffs 10, 50, 100 years down the road When we moved from more physical jobs to desk j…

> When we moved from more physical jobs to desk jobs many of us became sedentary and overweight. Now we are in an "obesity crisis". There's multiple factors to that, it's not just being in desk jobs, but being sedentary is a big factor.

Sure, although I think our lives are generally better than they were a few hundred years ago. Besides, if you care about your health you can always take steps yourself.

> The only one who benefits are the owners

Well yeah, the entity that benefits is the farm, and whoever owns whatever portions of the farm. The point of the farm isn't to give its workers jobs. It's to produce something to sell.

As long as we're in a market where we're selling our labor, we're only given money for being productive. If technology makes us redundant, then we find new jobs. Same as it ever was.

Think about it: why should hundreds of manual farmhands stay employed while they can be replaced by a single machine? That's not an efficient economy or society. Let those people re-skill and be useful in other roles.

Re: Human coders are still better than LLMs

#219

Post by vidarh »

jdiff wrote: post #91
cortesoft wrote: post #58

Earlier quoted context omitted.

Currently, I find AI to be a really good autocomplete

The crazy thing is that people think that a model designed to predict sequences of tokens from a stem, no matter how advanced the model, to be much more than just "really good autocomplete." It is impressive and very unintuitive just how far that can get you, but it's not reductive to use that label. That's what it is on a fundamental level, and aligning your usage with that will allow it to be more effective.

It's trivial to demonstrate that it takes only a tiny LLM + a loop to a have a Turing complete system. The extension of that is that it is utterly crazy to think that the fact it is "a model designed to predict sequences of tokens" puts much of a limitation on what an LLM can achieve - any Turing complete system can by definition simulate any other. To the extent LLMs are limited, they are limited by training and compute.

But these endless claims that the fact they're "just" predicting tokens means something about their computational power are based on flawed assumptions.

Re: Human coders are still better than LLMs

#220

Post by bbarn »

janalsncm wrote: post #92
loudmax wrote: post #83

Companies that leverage LLMs and AIs to let their employees be more productive will thrive. Companies that try to replace their employees with LLMs and AIs will fail. Unfortunately, all that's in the long run. In the near term, some CEOs and management teams will profit from the short term valuations as they squander their companies' future growth on short-sighted staff cuts.

Very well said. Using code assistance is going to be table stakes moving forward, not something that can replace people. It’s not like competitors can’t also purchase AI subscriptions.

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.
Post reply on HN