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

71–80 of 396 posts

Re: LLMs as the new high level language

#71

Post by runarberg »

hackyhacky wrote: post #36
cocoto wrote: post #31

Earlier quoted context omitted.

If there is no error on the compiler implementation and no undefined behavior the resulting program is equivalent and the few differences are mostly just implementation defined stuff which are left to the compiler to decide (but often gcc and clang do the same). The performance might differ also. It’s clearly not comparable to the many differences you can get from LLM’s output.

It just depends what level of abstraction you're willing to pretend doesn't matter. gcc and clang produce different assembly code, but it "does the same thing," for certain definitions of "same" and "thing." Claude and Gemini produce different Rust code, but it "does the same thing," for certain definitions of "same" and "thing." The issue is that the ultimate beneficiary of AI is the business owner. He's not a progr…

Your logic sounds like willful ignorance. You are relying on some odd definitions of "definitions", "equivalence", and "procedures". These are all rigorously defined in the underlying theory of computer science (using formal logic, lambda calculus, etc.)

Claude and Gemini do not "do the same thing" in the same way in which Clang and GCC does the same thing with the same code (as long as certain axioms of the code holds).

The C Standard has been rigorously written to uphold certain principles such that the same code (following its axioms) will always produce the same results (under specified conditions) for any standard compliant compiler. There exists no such standard (and no axioms nor conditions to speak of) where the same is true of Claude and Gemini.

If you are interested, you can read the standard here (after purchasing access): https://www.iso.org/obp/ui/#iso:std:iso-iec:9899:ed-5:v1:en

Re: LLMs as the new high level language

#72

Post by echelon »

beefsack wrote: post #22
dsr_ wrote: post #8

It's not a programming language if you can't read someone else's code, figure out what it does, figure out what they meant, and debug the difference between those things. "I prompted it like this" "I gave it the same prompt, and it came out different" It's not programming. It might be having a pseudo-conversation with a complex system, but it's not programming.

Prompting isn't programming. Prompting is managing.

Is it?

If I know the system I'm designing and I'm steering, isn't it the same?

We're not punching cards anymore, yet we're still telling the machines what to do.

Regardless, the only thing that matters is to create value.

Re: LLMs as the new high level language

#73

Post by mjr00 »

toprerules wrote: post #70
mjr00 wrote: post #64

Earlier quoted context omitted.

Surely at some point in your career as a SWE at FAANG you had to "dive deep" as they say and learn something that wasn't part of your "training data" to solve a problem?

I would have said the same thing a year or two ago, but AI is capable of doing deep dives. It can selectively clone and read dependencies outside of its data set. It can use tool calls to read documentation. It can log into machines and insert probes. It may not be better than everyone, but it's good enough and continuing to improve such that I believe subject matter expertise counts for much less.

I'm not saying that AI can't figure out how to handle bugs (it absolutely can; in fact even a decade ago at AWS there was primitive "AI" that essentially mapped failure codes to a known issues list, and it would not take much to allow an agent to perform some automation). I'm saying there will be situations the AI can't handle, and it's really absurd that you think a product owner will be able to solve deeply technical issues.

You can't product manage away something like "there's an undocumented bug in MariaDB which causes database corruption with spatial indexes" or "there's a regression in jemalloc which is causing Tomcat to memory leak when we upgrade to java 8". Both of which are real things I had to dive deep and discover in my career.

Re: LLMs as the new high level language

#74

Post by runarberg »

hackyhacky wrote: post #52
measurablefunc wrote: post #46

Earlier quoted context omitted.

I think you are b/c you lack actual understanding of how compilers work & what it would mean to compile the same C code w/ two different conformant C compilers & get semantically different results.

> you lack actual understanding of how compilers work My brother in Christ, please get off your condescending horse. I have written compilers. I know how they work. And also you've apparently never heard of undefined behavior. The point is that the output is different at the assembly level, but that doesn't matter to the user. Just as output from an LLM but differ from another, but the user doesn't care.

Undefined behavior is a edge case in C. Other programing languages (like JavaScript) goes to great lengths in defining their standards such that it is almost impossible to write code with undefined behavior. By far majority of code written out there has no undefined behavior. I think it is safe to assume that everyone here (except you) are talking about C code without undefined behavior when we mean that the same code produces the same results regardless of the compiler (as long as the compiler is standards conforming).

Re: LLMs as the new high level language

#75

Post by AlexeyBrin »

This is an exaggeration, if you store the prompt that was "compiled" by today's LLMs there is no guarantee that in 4 months from now you will be able to replicate the same result.

I can take some C or Fortran code from 10 years ago, build it and get identical results.

Re: LLMs as the new high level language

#76

Post by hackyhacky »

runarberg wrote: post #71
hackyhacky wrote: post #36

Earlier quoted context omitted.

It just depends what level of abstraction you're willing to pretend doesn't matter. gcc and clang produce different assembly code, but it "does the same thing," for certain definitions of "same" and "thing." Claude and Gemini produce different Rust code, but it "does the same thing," for certain definitions of "same" and "thing." The issue is that the ultimate beneficiary of AI is the business owner. He's not a progr…

Your logic sounds like willful ignorance. You are relying on some odd definitions of "definitions", "equivalence", and "procedures". These are all rigorously defined in the underlying theory of computer science (using formal logic, lambda calculus, etc.) Claude and Gemini do not "do the same thing" in the same way in which Clang and GCC does the same thing with the same code (as long as certain axioms of the code hol…

> Claude and Gemini do not "do the same thing" in the same way in which Clang and GCC does the same thing with the same code (as long as certain axioms of the code holds).

True, but none of that is relevant to the non-programmer end user.

> You are relying on some odd definitions of "definitions", "equivalence", and "procedures"

These terms have rigorous definitions for programmers. The person making software in the future is a non-programmer and doesn't care about any of that. They care only that the LLM can produce what they asked for.

> The C Standard has been rigorously written to uphold certain principles

I know what a standard is. The point is that the standard is irrelevant if you never look at the code.

Re: LLMs as the new high level language

#77

Post by runarberg »

hackyhacky wrote: post #76
runarberg wrote: post #71

Earlier quoted context omitted.

Your logic sounds like willful ignorance. You are relying on some odd definitions of "definitions", "equivalence", and "procedures". These are all rigorously defined in the underlying theory of computer science (using formal logic, lambda calculus, etc.) Claude and Gemini do not "do the same thing" in the same way in which Clang and GCC does the same thing with the same code (as long as certain axioms of the code hol…

> Claude and Gemini do not "do the same thing" in the same way in which Clang and GCC does the same thing with the same code (as long as certain axioms of the code holds). True, but none of that is relevant to the non-programmer end user. > You are relying on some odd definitions of "definitions", "equivalence", and "procedures" These terms have rigorous definitions for programmers. The person making software in the…

It is indeed extremely relevant to the end user. For websites the end user is not the creator of the web site who pushes it to the server, it is the user who opens it on a browser. And for that user it matters a great deal if a button is green or blue, if it responds to keyboard events, if it says “submit” or “continue”, etc. It also matters to the user whether their information is sent to a third party, whether their password is leaked, etc.

Your argument here (if I understand you correctly) is the same argument that to build a bridge you do not need to know all the laws of physics that prevents it from collapsing. The project manager of the construction team doesn’t need to know it, and certainly not the bicyclists who cross it. But the engineer who draws the blueprints needs to know it, and it matters that every detail on those blueprints are rigorously defined, such that the project manager of the construction team follows them to the letter. If the engineer does not know the laws of physics, or the project manager does not follow the blueprints to the letter, the bridge will likely collapse, killing the end user, that poor bicyclist.

Re: LLMs as the new high level language

#78

Post by jatora »

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…

i bet i could replicate it if you showed me the source file

Re: LLMs as the new high level language

#79

Post by jatora »

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…

If you're disconnected from cloud LLM's you've got bigger problems than coding can solve lol

Re: LLMs as the new high level language

#80

Post by jatora »

asa400 wrote: post #19
toprerules wrote: post #2

After working with the latest models I think these "it's just another tool" or "another layer of abstraction" or "I'm just building at a different level" kind of arguments are wishful thinking. You're not going to be a designer writing blueprints for a series of workers to execute on, you're barely going to be a product manager translating business requirements into a technical specification before AI closes that gap…

If all you (not you specifically, more of a royal “you” or “we”) are is a collection of skills centered around putting code into an editor and opening pull requests as fast as possible, then sure, you might be cooked. But if your job depends on taste, design, intuition, sociability, judgement, coaching, inspiring, explaining, or empathy in the context of using technology to solve human problems, you’ll be fine. The p…

Ah the age old 'but humans have heart, and no machine can replicate that' argument. Good luck!
Post reply on HN