LLMs as the new high level language • Hacker News Board

Re: LLMs as the new high level language

#331

Post by ChrisGreenHeur » Sun, Feb 08, 2026, 3:52 PM UTC

booleandilemma wrote: post #219

hndc wrote: post #95

Earlier quoted context omitted.

Deterministic compilation, aka reproducible builds, has been a basic software engineering concept and goal for 40+ years. Perhaps you could provide some examples of compilers that produce non-deterministic output along with your bad news.

Account created 11 months ago. They're probably just some slop artist with too much confidence. They probably don't even know what a compiler is.

He is a software engineer with a comp.sci masters degree with about 15 years industry experience with primarily C++. Currently employed at a company that you most likely know the name of.

Re: LLMs as the new high level language

#332

Post by ChrisGreenHeur » Sun, Feb 08, 2026, 3:53 PM UTC

whoisthemachine wrote: post #320

pjmlp wrote: post #236

Earlier quoted context omitted.

Not if they are dynamic compilers. Two runs of the same programme can produce different machine code from the JIT compiler, unless everything in the universe that happened in first execution run, gets replicated during the second execution.

Do these compilers sometimes give correct instructions and sometimes incorrect instructions for the same higher level code, and it's considered an intrinsic part of the compiler that you just have to deal with? Because otherwise this argument is bunk.

they in fact do have bugs, yes, inescapably so (no one provides formal proofs for production level compilers)

Re: LLMs as the new high level language

#333

Post by properbrew » Sun, Feb 08, 2026, 3:58 PM UTC

willj wrote: post #313

properbrew wrote: post #281

Earlier quoted context omitted.

> I want to see some assurance we get the same results every time Genuine question, but why not set the temperature to 0? I do this for non-code related inference when I want the same response to a prompt each time.

A temperature of 0 doesn’t result in the same responses every time, in part due to floating-point precision and in part to to lack of batch invariance [1] [1] https://thinkingmachines.ai/blog/defeating-nondeterminism-in...

Thank you for this, this was a really interesting read about batch invariance, something I didn't even know about.

Re: LLMs as the new high level language

#334

Post by ChrisGreenHeur » Sun, Feb 08, 2026, 3:59 PM UTC

Applejinx wrote: post #187

ChrisGreenHeur wrote: post #89

Earlier quoted context omitted.

I may have bad news for you on how compilers typically work.

I love the 'I may have' :)

made some people angry at me :)

Re: LLMs as the new high level language

#335

Post by senfiaj » Sun, Feb 08, 2026, 4:06 PM UTC

For me LLMs feel closer to IDE with steroids. Unless LLMs produce the same output from the same input, I can't view them as compilers.

Re: LLMs as the new high level language

#336

Post by onlyrealcuzzo » Sun, Feb 08, 2026, 4:26 PM UTC

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…

You're going to pretty hard pressed to do Rust better than Rust.

There's minimal opportunity with lifetime annotations. I'm sure very small options elsewhere, too.

The idea of replacing Rust with natural language seems insane. Maybe I'm being naive, but I can't see why or how it could possibly be useful.

Rust is simply Chinese unless you understand what it's doing. If you translate it to natural language, it's still gibberish, unless you understand what it does and why first. In which case, the syntax is nearly infinitely more expressive than natural language.

That's literally the point of the language, and it wasn't built by morons!

Re: LLMs as the new high level language

#337

Post by tomaytotomato » Sun, Feb 08, 2026, 4:36 PM UTC

cyberax wrote: post #10

tomaytotomato wrote: post #5

I would like to hijack the "high level language" term to mean dopamine hits from using an LLM. "Generate a Frontend End for me now please so I don't need to think" LLM starts outputting tokens Dopamine hit to the brain as I get my reward without having to run npm and figure out what packages to use Then out of a shadowy alleyway a man in a trenchcoat approaches "Pssssttt, all the suckers are using that tool, come try…

> and your muscle memory for running maven commands Here's $1000. Please do that. Don't bother with the LLM.

I'm guessing you like Gradle? :)

Re: LLMs as the new high level language

#338

Post by manuelabeledo » Sun, Feb 08, 2026, 4:43 PM UTC

onlyrealcuzzo wrote: post #336

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…

You're going to pretty hard pressed to do Rust better than Rust. There's minimal opportunity with lifetime annotations. I'm sure very small options elsewhere, too. The idea of replacing Rust with natural language seems insane. Maybe I'm being naive, but I can't see why or how it could possibly be useful. Rust is simply Chinese unless you understand what it's doing. If you translate it to natural language, it's still…

I believe the author thinks of this problem in terms of “the LLM will figure it out”, i.e. it will be trained on enough code that compiles, that the LLM just needs to put the functional blocks together.

Which might work to a degree with languages like JavaScript.

Re: LLMs as the new high level language

#339

Post by Razengan » Sun, Feb 08, 2026, 4:53 PM UTC

If you see magazines, articles, ads and TV shows from the 1980s (there are lots on YouTube and a fun rabbit hole, like the BBC Archive), the general promise was "Computers can do anything, if you program them."

Well, nobody could figure out how to program them. Except the few outcasts like us who went on to suffer for the rest of our lives for it :')

With phones & LLMs this is the closest we have come to that original promise of a computer in every home and everyone being able to do anything with it, that isn't pre-dictated by corporations and their apps:

Ideally ChatGPT etc should be able to create interactive apps on the fly on iPhone etc. Imagine having a specific need and just being able to say it and get an app right away just for you on your device.

Re: LLMs as the new high level language

#340

Post by podgorniy » Sun, Feb 08, 2026, 4:53 PM UTC

I want to see an example of the application with well written documentation which produces well working application based on those docs.

I discovered that it is not trivial to conceptualize app to that extent of clarity which is required for deterministic output of LLM. It's way easier to say than to actually implement by yourself (that's why examples are so interesting to see).

Backwards dynamics when you get spec/doc based on the source code does not work good enough.