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

81–90 of 396 posts

Re: LLMs as the new high level language

#81

Post by orbital-decay »

isodev wrote: post #38
orbital-decay wrote: post #28

Earlier quoted context omitted.

>"I prompted it like this" >"I gave it the same prompt, and it came out different" 1:1 reproducibility is much easier in LLMs than in software building pipelines. It's just not guaranteed by major providers because it makes batching less efficient.

> 1:1 reproducibility is much easier in LLMs than in software building pipelines What’s a ‘software building pipeline’ in your view here? I can’t think of parts of the usual SDLC that are less reproducible than LLMs, could you elaborate?

Reproducibility across all existing build systems took a decade of work involving everything from compilers to sandboxing, and a hard reproducibility guarantee in completely arbitrary cases is either impossible or needs deterministic emulators which are terribly slow. (e.g. builds that depend on hardware probing or a simulation result)

Input-to-output reproducibility in LLMs (assuming the same model snapshot) is a matter of optimizing the inference for it and fixing the seed, which is vastly simpler. Google for example serves their models in an "almost" reproducible way, with the difference between runs most likely attributed to batching.

Re: LLMs as the new high level language

#82

Post by apical_dendrite »

toprerules wrote: post #25
asa400 wrote: post #19

Earlier quoted context omitted.

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…

The question isn't whether businesses will have 0 human element to them, the question is does AI offer a big enough gap that technical skills are still required such that technical roles are still hired for. Someone in product can have all of those skills without a computer science degree, with no design experience, and AI will do the technical work at the level of design, implementation, and maintenance. What I am s…

I am only seeing that if the person writing the prompts knows what a quality solution looks like at a technical level and is reviewing the output as they go. Otherwise you end up with an absolute mess that may work at least for "happy path" cases but completely breaks down as the product needs change. I've described a case of this in some detail in another comment.

Re: LLMs as the new high level language

#83

Post by spacephysics »

OutOfHere wrote: post #55

The side effect of using LLMs for programming is that no new programming language can now emerge to be popular, that we will be stuck with the existing programming languages forever for broad use. Newer languages will never accumulate enough training data for the LLM to master them. Granted, non-LLM AIs with true neural memory can work around this, as can LLMs with an infinite token frozen+forkable context, but these…

I wouldn’t be surprised if in the next 5-10 years the new and popular programming language is one built with the idea of optimizing how well LLM’s (or at that point world models) understand and can use it.

Right now LLMs are taking languages meant for humans to understand better via abstraction, what if the next language is designed for optimal LLM/world model understanding?

Or instead of an entirely new language, theres some form of compiling/transpiling from the model language to a human centric one like WASM for LLMs

Re: LLMs as the new high level language

#84

Post by prxm »

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…

This is one of my favourite activites with LLMs as well. After implementing some sort of idea for an algorithm, I try seeing what an LLM would come up with. I hint it as well and push it in the correct direction with many iterations but never tell the most ideal one. And as a matter of fact they can never reach the quality I did with my initial implementation.

Re: LLMs as the new high level language

#85

Post by hackyhacky »

runarberg wrote: post #74
hackyhacky wrote: post #52

Earlier quoted context omitted.

> 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 cod…

Language-based undefined behavior is just one kind of nondeterminism that programmers deal with every day. There are other examples, such as concurrency. So that claim that using LLMs isn't programming because "nondeterminism" makes no sense.

Re: LLMs as the new high level language

#86

Post by danparsonson »

apical_dendrite wrote: post #18

I'm trying to work with vibe-coded applications and it's a nightmare. I am trying to make one application multi-tenant by moving a bunch of code that's custom to a single customer into config. There are 200+ line methods, dead code everywhere, tons of unnecessary complexity (for instance, extra mapping layers that were introduced to resolve discrepancies between keys, instead of just using the same key everywhere). N…

You've just described the entirely-human-made project that I'm working on now.... at least now we can deliver the intractable mess much more quickly!

Re: LLMs as the new high level language

#88

Post by danparsonson »

TZubiri wrote: post #4

"Following this hypothesis, what C did to assembler, what Java did to C, what Javascript/Python/Perl did to Java, now LLM agents are doing to all programming languages." This is not an appropriate analogy, at least not right now. Code Agents are generating code from prompts, in that sense the metaphor is correct. However Agents then read the code and it becomes input and they generate more code. This was never the ca…

I think it's appropriate in terms of the results rather than the process; the bigger problem I see is that programming languages are designed to be completely unambiguous, whereas human language is not ("Go to the shop and buy one box of eggs, and if they have carrots, buy three") so we're transitioning from exactly specifying what we want the software to do, to tying ourselves in knots trying to specify it exactly, while a machine tries to disambiguate our request. I bet lawyers would make good vibe coders.

Re: LLMs as the new high level language

#90

Post by kranner »

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'm seeing the same thing with my own little app that implements several new heuristics for functionality and optimisation over a classic algorithm in this domain. I came up with the improvements by implementing the older algorithm and just... being a human and spending time with the problem.

The improvements become evident from the nature of the problem in the physical world. I can see why a purely text-based intelligence could not have derived them from the specs, and I haven't been able to coax them out of LLMs with any amount of prodding and persuasion. They reason about the problem in some abstract space detached from reality; they're brilliant savants in that sense, but you can't teach a blind person what the colour red feels like to see.

Post reply on HN