LLMs as the new high level language • Hacker News Board

Re: LLMs as the new high level language

#391

Post by fpereiro » Mon, Feb 09, 2026, 8:48 AM 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…

@manuelabeledo: during 2025 I've been building a programming substrate called cell (think language + environment) that attempts to be both very compact and very expressive. Its goal is to massively reduce complexity to turn general purpose code more understandable (I know this is laughably ambitious and I'm desperately limited in my capabilities of pulling through something like that). But because of the LLM tsunami, I'm reconsidering the role of cell (or any other successful substrate): even if we achieve the goal, how will this interact with a world where people mostly write and validate code through natural language prompts? I never meant to say that natural language would itself be this substrate, or that the combination of LLMs and natural languages could do that: I still see that there will be a programming language behind all of this. Apologies for the confusion.

Re: LLMs as the new high level language

#392

Post by fpereiro » Mon, Feb 09, 2026, 8:48 AM UTC

heikkilevanto wrote: post #226

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. A traditional compiler will produce a program that behaves the same way, given the same source and options. Some even go out of their way to guarantee they produce the same binary output, which is a good thing for security and package management. That is why we don't need to store the…

Mario Zechner has a very interesting article where he deals with this problem (https://mariozechner.at/posts/2025-06-02-prompts-are-code/#t...). He's exploring how structured, sequential prompts can achieve repeatable results from LLMs, which you still have to verify. I'm experimenting with the same, though I'm just getting started. The idea I sense here is that perhaps a much tighter process of guiding the LLM, with current models, can get you repeatable and reliable results. I wonder if this is the way things are headed.

Re: LLMs as the new high level language

#393

Post by fpereiro » Mon, Feb 09, 2026, 8:49 AM UTC

WoodenChair wrote: post #98

The article starts with a philosophically bad analogy in my opinion. C-> Java != Java -> LLM because the intermediate product (the code) changed its form with previous transitions. LLMs still produce the same intermediate product. I expanded on this in a post a couple months back: https://www.observationalhazard.com/2025/12/c-java-java-llm.... "The intermediate product is the source code itself. The intermediate goal…

I think that we can already experience a revolution with LLMs that are not fully autonomous. The potential is that an engineering-like approach to a prompt flow can allow you to design and review (not write) a lot more code than before. Though you're 100% correct that the analogy doesn't strictly hold until we can stop looking at the code in the same way that a js dev doesn't look at what the interpreter is emitting.

Re: LLMs as the new high level language

#394

Post by fpereiro » Mon, Feb 09, 2026, 8:49 AM UTC

nly wrote: post #27

I have a source file of a few hundred lines implementing an algorithm that no LLM I've tried (and I've tried them all) is able to replicate, or even suggest, when prompted with the problem. Even with many follow up prompts and hints. The implementations that come out are buggy or just plain broken The problem is a relatively simple one, and the algorithm uses a few clever tricks. The implementation is subtle...but no…

Great point. The thing is that most code we write is not elegant implementations of algorithms, but mostly glue or CRUDs. So LLMs can still broadly be useful.

Re: LLMs as the new high level language

#395

Post by mike_hearn » Mon, Feb 09, 2026, 10:50 AM UTC

hndc wrote: post #358

mike_hearn wrote: post #199

Earlier quoted context omitted.

JIT compilers.

Compiler artifact is still deterministic. Clearly not referring to runtime behavior that is input-dependent

The output of the compiler isn't deterministic. It depends a lot on timing and how that affects the profiles.

Re: LLMs as the new high level language

#396

Post by sarchertech » Mon, Feb 09, 2026, 1:07 PM UTC

orbital-decay wrote: post #388

sarchertech wrote: post #377

Earlier quoted context omitted.

That’s the whole thesis of the article. Using an LLM as a high level language. >The codebase should be reconstructable from the documentation

And this kind of reproducibility is insensitive to prompt instability. If your inference is deterministic (trivial if within the lifetime of a snapshot), you give it the same docs and get the same result.

Obviously this article is advocating for spec as source code and not checking in code to keep it around between “compilations”.

Why would you care about reproducibility at all if you were checking in the code as well. If you check in the code, you’d never need to rerun the same prompt.