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

LLMs as the new high level language

federicopereiro.com

Post reply on HN
Print view View original

361–370 of 396 posts

Re: LLMs as the new high level language

#361

Post by carlmr »

devsda wrote: post #360
afavour wrote: post #317

Earlier quoted context omitted.

> If we consider the prompts and LLM inputs to be the new source code, I want to see some assurance we get the same results every time. There’s a related issue that gives me deep concern: if LLMs are the new programming languages we don’t even own the compilers. They can be taken from us at any time. New models come out constantly and over time companies will phase out older ones. These newer models will be better, s…

> New models come out constantly and over time companies will phase out older ones. These newer models will be better, sure, but their outputs will be different. IIUC, same model with same seed and other parameters is not guaranteed to produce the same output. If anyone is imagining a future where your "source" git repo is just a bunch of highly detailed prompt files and "compilation" just needs an extra LLM code gen…

>IIUC, same model with same seed and other parameters is not guaranteed to produce the same output.

Models are so large that random bit flips make such guarantees impossible with current computing technology:

https://aclanthology.org/2025.emnlp-main.528.pdf

Re: LLMs as the new high level language

#362

Post by manuelabeledo »

coldtea wrote: post #350
manuelabeledo wrote: post #312

After re-reading the post once again, because I honestly thought I was missing something obvious that would make the whole thing make sense, I started to wonder if the author actually understands the scope of a computer language. When he says: > LLMs are far more nondeterministic than previous higher level languages. They also can help you figure out things at the high level (descriptions) in a way that no previous l…

> After re-reading the post once again, because I honestly thought I was missing something obvious that would make the whole thing make sense, I started to wonder if the author actually understands the scope of a computer language. The problem is you restrict the scope of a computer language to the familiar mechanisms and artifacts (parsers, compilers, formalized syntax, etc), instead of taking to be "something we in…

If you cannot even provide a clear definition of what you want it to be, then this is all science fiction.

Re: LLMs as the new high level language

#363

Post by manuelabeledo »

pjmlp wrote: post #353
manuelabeledo wrote: post #283

Earlier quoted context omitted.

For a single execution, to a certain extent, yes. But that’s not the point I’m trying to make here. JIT compilers are vastly more predictable than LLMs. I can take any two JVMs from any two vendors, and over several versions and years, I’m confident that they will produce the same outputs given the same inputs, to a certain degree, where the input is not only code but GC, libraries, etc. I cannot do the same with two…

Good luck mapping OpenJDK with Azul's cloud JIT, in generated machine code.

The output being the actual program output, not the byte code. No one is arguing that in the scope of LLMs.

Re: LLMs as the new high level language

#364

Post by coldtea »

manuelabeledo wrote: post #362
coldtea wrote: post #350

Earlier quoted context omitted.

> After re-reading the post once again, because I honestly thought I was missing something obvious that would make the whole thing make sense, I started to wonder if the author actually understands the scope of a computer language. The problem is you restrict the scope of a computer language to the familiar mechanisms and artifacts (parsers, compilers, formalized syntax, etc), instead of taking to be "something we in…

If you cannot even provide a clear definition of what you want it to be, then this is all science fiction.

Doesn't have to be "a clear definition", a rough defition within some quite lax boundaries is fine.

You can just say to Claude for example "Make me an app that accepts daily weight measurements and plots them in a graph" and it will make one. Tell it to use tha framework or this pattern, and it will do so too. Ask for more features as you go, in similar vague language. At some point your project is done.

Even before AI the vast majority of software is not written with any "clear definition" to begin with, there's some rought architecture and idea, and people code as they go, and often have to clarify or rebuilt things to get them as they want, or discover they want something slightly different or the initial design had some issues and needs changing.

Re: LLMs as the new high level language

#365

Post by skaul »

redox99 wrote: post #355
skaul wrote: post #347

Programming with LLMs is fundamentally different than going from a lower-level to a higher-level language, even apart from the whole non-determinism thing. With a programming language, you're still writing a for-loop, whether that's in C, Java or Rust. There's language primitives that help you think better in certain languages, but they're still, at the end of the day, code and context that you have to hold in your h…

A programming language does not need to have a for loop. In fact many don't.

Programming languages need to give the developer a way to iterate (map, fold, for-loop, whatever) over a collection of items. Over time we've come up with more elegant ways of doing this, but as a programmer, until LLMs, you've still had to be actively involved in the control logic. My point is that a developer's relationship with the code is very different now, in a way that wasn't true with previous low-to-high level language climbs.

Re: LLMs as the new high level language

#366

Post by collingreen »

coldtea wrote: post #364
manuelabeledo wrote: post #362

Earlier quoted context omitted.

If you cannot even provide a clear definition of what you want it to be, then this is all science fiction.

Doesn't have to be "a clear definition", a rough defition within some quite lax boundaries is fine. You can just say to Claude for example "Make me an app that accepts daily weight measurements and plots them in a graph" and it will make one. Tell it to use tha framework or this pattern, and it will do so too. Ask for more features as you go, in similar vague language. At some point your project is done. Even before…

This is the most handwaving per paragraph I've ever seen.

I think a fair summarization of your point is "LLM generated programs work well enough often enough to not need more constraints or validation than natural language", whatever that means.

If you take that as a true thing then sure why would you go deeper (eg, I never look at the compiled bytecode my high level languages produce for this exact reason - I'm extremely confident that translation is right to the point of not thinking about it anymore).

Most people who have built, maintained, and debugged software aren't ready to accept the premise that all of this is just handled well by LLMs at this point. Many many folks have lots of first hand experience watching it not be true, even when people are confidently claiming otherwise.

I think if you want to be convincing in this thread you need to go back one step and explain why the LLM code is "good enough" and how you determined that. Otherwise it's just two sides talking totally past each other.

Re: LLMs as the new high level language

#368

Post by PunchyHamster »

pavlov wrote: post #161
PunchyHamster wrote: post #156

At this point I'm just waiting for people claiming they managed team of 20 people, where "20 people" were LLMs being fed a prompt

This claim has been going around for a while. I know someone who has been spending $7k / month on Cursor tokens for the past six months, managing such a team of agents… But curiously the results seem to be endless PDF-ware, and every month there’s a new reason why the project is not yet quite ready to be used on real data. LLMs are very good at making you think they’re giving you what you hoped to get.

There are clearly uses where it can be very useful, if you just want to prototype some solutions having AI-throwaway code that you don't understand is entirely fine

But if you commit that and turn it into production project... that's basically starting with massive tech debt from the get go, and you can't do "just let AI write it from scratch again" trick too many times while growing features

Re: LLMs as the new high level language

#369

Post by coldtea »

collingreen wrote: post #366
coldtea wrote: post #364

Earlier quoted context omitted.

Doesn't have to be "a clear definition", a rough defition within some quite lax boundaries is fine. You can just say to Claude for example "Make me an app that accepts daily weight measurements and plots them in a graph" and it will make one. Tell it to use tha framework or this pattern, and it will do so too. Ask for more features as you go, in similar vague language. At some point your project is done. Even before…

This is the most handwaving per paragraph I've ever seen. I think a fair summarization of your point is "LLM generated programs work well enough often enough to not need more constraints or validation than natural language", whatever that means. If you take that as a true thing then sure why would you go deeper (eg, I never look at the compiled bytecode my high level languages produce for this exact reason - I'm extr…

>This is the most handwaving per paragraph I've ever seen.

Yes: "LLM generated programs work well enough often enough to not need more constraints or validation than natural language" if a fair summarization of my point.

Not sure the purpose of "whatever that means" that you added. It's clear what it means. Thought, casual language seems to be a problem for you. Do you only always discuss in formally verified proofs? If so, that's a you problem, not an us or LLM problem :)

>Most people who have built, maintained, and debugged software aren't ready to accept the premise that all of this is just handled well by LLMs at this point.

I don't know who those "most people are". Most developers already hand those tasks to LLMs, and more will in the future, as it's a market/job pressure.

(I'm not saying it's good or good enough as a quality assessment. In fact, I don't particularly like it. But I am saying it's "good enough" as in, people will deem it good enough to be shipped).

Re: LLMs as the new high level language

#370

Post by redox99 »

skaul wrote: post #365
redox99 wrote: post #355

Earlier quoted context omitted.

A programming language does not need to have a for loop. In fact many don't.

Programming languages need to give the developer a way to iterate (map, fold, for-loop, whatever) over a collection of items. Over time we've come up with more elegant ways of doing this, but as a programmer, until LLMs, you've still had to be actively involved in the control logic. My point is that a developer's relationship with the code is very different now, in a way that wasn't true with previous low-to-high lev…

I was thinking of something like SQL, which is declarative and you tell it what you want, not how to do it broadly speaking.
Post reply on HN