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

Let's talk about LLMs

b-list.org

Post reply on HN
Print view View original

141–150 of 201 posts

Re: Let's talk about LLMs

#141

Post by Leynos »

gerdesj wrote: post #91
mfro wrote: post #4

I think you're misunderstanding the paradigm shift completely -- AI does not just generate code N(x) more quickly. It thinks N(x) faster, it researches N(x) faster, it tests N(x) faster. There are hundreds of tasks that you'll find engineers are offloading to AI every day. The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows. This is why tool-use and a…

"paradigm shift" A paradigm shift is an earth shattering, very important change - a complete change in thinking etc. LLMs are not that. They are simply some pretty new tools. Nice tools but they will whip off your metaphorical thumb just as quickly as a miss-used table saw. You'll note that you mention "engineers are offloading": that's not a paradigm shift. That's a bunch of engineers discovering a better slide rule…

When the nature of your job changes fundamentally in the space of a year, "paradigm shift" feels unsettlingly appropriate.

Re: Let's talk about LLMs

#142

Post by viking123 »

aspenmartin wrote: post #99
gerdesj wrote: post #91

Earlier quoted context omitted.

"paradigm shift" A paradigm shift is an earth shattering, very important change - a complete change in thinking etc. LLMs are not that. They are simply some pretty new tools. Nice tools but they will whip off your metaphorical thumb just as quickly as a miss-used table saw. You'll note that you mention "engineers are offloading": that's not a paradigm shift. That's a bunch of engineers discovering a better slide rule…

I would argue LLMs are possibly the largest paradigm shift the world has ever seen, and we are only at the beginning. The entire scaffolding and structure of programming is in the process of changing — coding has moved to orchestration and testing and governance of how to manage and productionalize code that has surpassed the capacity of human review. If this sounds melodramatic it’s likely that it hasn’t fully taken…

lmao

Re: Let's talk about LLMs

#143

Post by prmph »

mfro wrote: post #4

I think you're misunderstanding the paradigm shift completely -- AI does not just generate code N(x) more quickly. It thinks N(x) faster, it researches N(x) faster, it tests N(x) faster. There are hundreds of tasks that you'll find engineers are offloading to AI every day. The major hurdle right now is actually pivoting LLMs from just generating code: integrating those tasks into workflows. This is why tool-use and a…

> It thinks faster

It does not actually, and not any faster.

Again I've lost count of how many times I've had an in-depth architectural discussion with ChatGPT, with it giving me the final mark of approval ("This is excellent"), only for me to discover a flaw in my approach or a radically simpler and better approach, go back to it with it, and for it to proclaim "Yeah this is a much better approach".

These LLMs are in many cases sycophantic confirmation machines. Yes, they are useful to some extent in helping you refine your ideas and think of edge cases. But they are nowhere close to actually thinking better and faster. Faster in the wrong direction is not just slow, you are actually going backward.

Re: Let's talk about LLMs

#144

Post by zouhair »

marcus_holmes wrote: post #133
zouhair wrote: post #109

Earlier quoted context omitted.

The problem I have with it is the price (I am not talking about the money). I don't know if the price is worth it. For example we are literally witnessing the death of the personal computers, it will soon become a rich people's hobby. I don't know how the whole Free Software/Open source will survive that. At best we will end up not owning nothing, not even the programming skills as everyone will be at the mercy of AI…

I'm not sure what LLMs have to do with the death of personal computers? Can you explain, please?

Prices of RAM, GPUs, SSDs and even HDDs are now way out of reach for many people [0]. An SSD I bought 2 years ago at $300 CAD now cost $1K CAD for example and it's not gonna go down any time soon.

[0]: https://www.tomshardware.com/pc-components/storage/perfect-s...

Re: Let's talk about LLMs

#145

Post by prmph »

hombre_fatal wrote: post #72
smartmic wrote: post #19

Earlier quoted context omitted.

> I'm sure it was very difficult to program in machine code, but if now (or soon) anyone can just write software using a LLM without any sort of learning it changes everything. LLMs can plan and create something usable from simple instructions or ideas, and they will only get better. Did you read the section "Power to the People?" ? In it, the author dismantles your thesis with powerful, highly plausible arguments.

I read that section but I disagree with it. 1. You don't have to be an LLM expert to get good, consistent results with LLMs. My best vibe-code process after years of using LLMs is to have Claude Code create a plan file and then cycle it through Codex until Codex finds nothing more to review, then have an agent implement it. This process is trivial yet produces amazing results. It's solved by better and better harness…

This sounds like someone who have never had to write serious software.

> 1. You don't have to be an LLM expert to get good, consistent results with LLMs.

You don't get good consistent results with LLMs, expert or not

> 2. You don't have to write technical specs. The LLM does that for you. You just tell it "I want the next-tab button to wrap back to the first one" and it generates a technical plan. Natural language is fine.

Try this, have Claude write a section in your specs titled "Performance Optimizations" and see the gibberish it will come up with. Fluffy lists with no actually useful content specific to the project. This is a severe problem with LLM-driven speccing I have encountered uncountable times. I now rarely allow them to touch the specs document.

> 3. Software that seems to work only to fail down the line in production is already how software works today. With LLMs you can paste the stacktrace or user bug email and it will fix it.

And pretty soon you have a big ball of mud. But I guess if the rate of bugs accelerate, the LLMs can also "fix" them faster

> This is why vibe-coding works. Instead of simulating how an app will run in your head looking at its code, you run the app and tell the LLM what isn't working correctly. The app spec is derived iteratively through a UX feedback look.

I should tell you about the markdown viewer with specific features I want, that I have wanted to build only with LLM vibe-coding, and how none of them are able to do it.

Re: Let's talk about LLMs

#146

Post by marcus_holmes »

zouhair wrote: post #144
marcus_holmes wrote: post #133

Earlier quoted context omitted.

I'm not sure what LLMs have to do with the death of personal computers? Can you explain, please?

Prices of RAM, GPUs, SSDs and even HDDs are now way out of reach for many people [0]. An SSD I bought 2 years ago at $300 CAD now cost $1K CAD for example and it's not gonna go down any time soon. [0]: https://www.tomshardware.com/pc-components/storage/perfect-s...

Ah I see, yeah.

This feels like classic economics, though - if the price of something goes up because of demand, then more suppliers enter the market and supply increases.

Also, the AI thing is a bubble, and bubbles burst. Sooner or later all that demand is going to disappear and we'll be oversupplied.

But yes, interesting times indeed.

Re: Let's talk about LLMs

#147

Post by soco »

empthought wrote: post #83
strange_quark wrote: post #52

Earlier quoted context omitted.

I've had a similar thought. A super refactor feature would be amazing, but wouldn't fit into the current zeitgeist of agent everything. Hopefully as the hype starts to die down and prices go up, we'll get some of these smaller, more targeted features.

You don't need a special feature for this. Just tell the coding assistant what to do.

Then watch it f'up half your codebase because it thinks it's slightly related to your examples. The alternative, giving it 10 examples, is actually more work.

Re: Let's talk about LLMs

#148

Post by viking123 »

jatora wrote: post #139
zapataband1 wrote: post #135

Earlier quoted context omitted.

ah yes another feeble fool that thinks his 100$ subscription is equivalent to 400 billion years of evolution simply because he is stupid and watches a lot of scifi.

Nope not at all, but it's most certainly superior to the tokens your neural net outputs

say that you are alive

"i am alive"

OH MY GOD!!

Re: Let's talk about LLMs

#149

Post by slopinthebag »

jatora wrote: post #121
zapataband1 wrote: post #93

Earlier quoted context omitted.

How many years of real-life, in-production problem solving/coding have you done? That's what I base how informed you are not how much you use your favorite new $100/month token-prediction subscription

15 years. But that's irrelevant to this point. The person im replying to clearly doesnt use the tools if they think there hasnt been constant improvement. "token-prediction subscription" is funny, coming from a glorified biological token predictor

I'm starting to think the AI maxis are just misanthropes.

Re: Let's talk about LLMs

#150

Post by slopinthebag »

aspenmartin wrote: post #115
slopinthebag wrote: post #49

Earlier quoted context omitted.

Yes but we don't know the shape of the curve and where we are on it.

See chinchilla scaling laws, we have the functional form of the curve and know the constants (though they change and are domain and model specific): L(N,D) ~= 1.69 + 406 / N^0.339 + 411 / D^0.285 L is loss (pre training test loss) D is the scale of the data N is the number of model parameters

You need to touch grass dude, seriously.
Post reply on HN