LLMs as the new high level language • Hacker News Board

Re: LLMs as the new high level language

#341

Post by nerdsniper » Sun, Feb 08, 2026, 4:55 PM UTC

afavour wrote: post #317

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…

> 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…

Presumably, open models will work almost, but not quite, as well and you can store those on your local drive and spin them up in rented GPUs.

Re: LLMs as the new high level language

#342

Post by hackyhacky » Sun, Feb 08, 2026, 5:02 PM UTC

JackSlateur wrote: post #327

hackyhacky wrote: post #33

Earlier quoted context omitted.

> In my experience, agentic LLMs tend to write code that is very branchy with cyclomatic complexity You are missing the forest for the trees. Sure, we can find flaws in the current generation of LLMs. But they'll be fixed. We have a tool that can learn to do anything as well as a human, given sufficient input.

We have heard that for years "trust us, it will work soon .. we just need a bit more time and a couple more dozens billions of dollars .. just trust us, bro .."

> We have heard that for years

LLMs have been a thing for about three years now, so you can't have been hearing this for very long. In those three years, the rate of progress has been astounding and there is no sign of slowing down.

Re: LLMs as the new high level language

#343

Post by kittbuilds » Sun, Feb 08, 2026, 5:07 PM UTC

[dead]

Re: LLMs as the new high level language

#344

Post by FuckButtons » Sun, Feb 08, 2026, 5:07 PM UTC

voxleone wrote: post #308

One thing I think the “LLM as new high-level language” framing misses is the role of structure and discipline. LLMs are great at filling in patterns, but they struggle with ambiguity, the exact thing we tolerate in human languages. A practical way to get better results is to stop prompting with prose and start providing explicit models of what we want. In that sense, UML-like notations can act as a bridge between hum…

Have you tried this? How did it go?

Re: LLMs as the new high level language

#345

Post by hackyhacky » Sun, Feb 08, 2026, 5:07 PM UTC

heavyset_go wrote: post #274

hackyhacky wrote: post #29

Earlier quoted context omitted.

> The irony is that I haven't seen AI have nearly as large of an impact anywhere else. We are in this pickle because programmers are good at making tools that help programmers. Programming is the tip of the spear, as far as AI's impact goes, but there's more to come. Why pay an expensive architect to design your new office building, when AI will do it for peanuts? Why pay an expensive lawyer to review your contract?…

> Why pay an expensive architect to design your new office building, when AI will do it for peanuts? Why pay an expensive lawyer to review your contract? Why pay a doctor, etc. All of those jobs are mandated by law to done by accredited and liable humans.

> All of those jobs are mandated by law to done by accredited and liable humans.

Good point. The jobs I listed will be protected for a little while due to statutory limitations. At first, firms will have one AI-augmented lawyer take on the work of a dozen lawyers. Of course his salary won't increase, and the others will be fired. Eventually, he'll just be rubber-stamping the AI's results, purely for the sake of compliance. Then the ruling class will petition the legislature to change the law in the name of "efficiency," and that will be the end of that.

Meanwhile, programmers have no such protection. Nor do customer service agents, secretaries, publishers, copywriters, banker, office managers. There is no safety net.

Re: LLMs as the new high level language

#346

Post by hackyhacky » Sun, Feb 08, 2026, 5:13 PM UTC

mike_hearn wrote: post #204

hackyhacky wrote: post #29

Earlier quoted context omitted.

> The irony is that I haven't seen AI have nearly as large of an impact anywhere else. We are in this pickle because programmers are good at making tools that help programmers. Programming is the tip of the spear, as far as AI's impact goes, but there's more to come. Why pay an expensive architect to design your new office building, when AI will do it for peanuts? Why pay an expensive lawyer to review your contract?…

> Why pay an expensive architect to design your new office building, when AI will do it for peanuts? Will it? AI is getting good at some parts of programming because of RLVR. You can test architectural designs automatically to some extent but not entirely, because people tend to want unique buildings that stand out (if it weren't the case architects would have already become a niche profession due to everyone using p…

> people tend to want unique buildings that stand out

Just tell the LLM that you want a unique design. I've found LLMs to respond well to requests for "originality," at least in poetry, prose, and coding. No reason that can't do that in architecture as well.

> At some point an architectural design has to be built and you can't currently simulate real building sites at high speed inside a datacenter.

First of all, you can simulate a building site, or any physical environment. We've been doing that for years, even in games. AI companies are working towards a "world model" for precisely that reason. Second of all, even without a physical simulation, the laws of physics are deterministic and easy for an LLM to understand.

> The safe jobs are ones where there's little training data available online,

These cases are "safe" only in relative terms. Lack of easily-available training data is friction but not insurmountable. AI companies have bet big and they have a strong incentive to find and use appropriate training data.

Re: LLMs as the new high level language

#347

Post by skaul » Sun, Feb 08, 2026, 5:16 PM UTC

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 head and be intimately familiar with.

That changes with LLMs. For now, you can use LLMs to help you code that way; a programming buddy whose code you review. That's soon going to become "quaint" (to quote the author) given the projected productivity gains of agents (and for many developers it already has).

Re: LLMs as the new high level language

#348

Post by pjmlp » Sun, Feb 08, 2026, 5:19 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.

Possibly, hence why the discussion regarding security in JavaScript runtimes and JIT, by completely disabling JIT execution.

https://microsoftedge.github.io/edgevr/posts/Super-Duper-Sec...

Also the exact sequence of generated machine instructions depends of various factors, the same source can have various outputs, depending on code execution, preset hardware, and heuristics.

Re: LLMs as the new high level language

#349

Post by pjmlp » Sun, Feb 08, 2026, 5:23 PM UTC

sarchertech wrote: post #294

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.

That’s 100% correct, but importantly JIT compilers are built with the goal of outputting semantically equivalent instructions. And the vast, vast majority of the time, adding a new line to the source code will not result in an unrecognizably different output. With an LLM changing one word can and frequently does cause the out to be so 100% different. Literally no lines are the same in a diff. That’s such a vastly dif…

No, but will certainly result in a complete different sequence of machine code instructions, or not, depending on what that line actually does, what dynamic types it uses, how often it actually gets executed, the existence of vector units, and so forth.

Likewise, as long as the agent delivers the same outcome, e.g. an email is sent with a specific subject and body, the observed behaviour remains.

Re: LLMs as the new high level language

#350

Post by coldtea » Sun, Feb 08, 2026, 5:23 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…

>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 instruct the computer with, so that it does what we want".

>How does this even work? There is no universe I can imagine where a natural language can be universal, self descriptive, non ambiguous, and have a smaller footprint than any purpose specific language that came before it.

Doesnt matter. Who said it needs to be "universal, self descriptive, non ambiguous, and have a smaller footprint than any purpose specific language that came before it"?

It's enough that is can be used to instruct computers more succintly and at a higher level of abstraction, and that a program will come out at the end, which is more or less (doesn't have to be exact), what we wanted.