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

61–70 of 396 posts

Re: LLMs as the new high level language

#61

Post by hackyhacky »

mjr00 wrote: post #58
hackyhacky wrote: post #56

Earlier quoted context omitted.

> which completely changes the way the website has to be hosted--this category matters quite a bit, no? It matters to you because you're a programmer, and you can't imagine how someone could create a program without being a programmer. But it doesn't really matter. The non-technical user of the LLM won't care if the LLM generates PHP or JS code, because they don't care how it gets hosted. They'll tell the LLM to take…

Is the LLM paying for hosting in this scenario, too? Is the LLM signing up for the new hosting provider that supports PHP after initially deploying to github pages? Feels like the non-programmer is going to care a little bit about paying for 5 different hosting providers because the LLM decided to generate their burger website in PHP, JavaScript, Python, Ruby and Perl in successive iterations.

> Is the LLM paying for hosting in this scenario, too? Is the LLM signing up for the new hosting provider that supports PHP after initially deploying to github pages?

It's an implementation detail. The user doesn't care. OpenClaw can buy its own hosting if you ask it to.

> Feels like the non-programmer is going to care a little bit about paying for 5 different hosting providers because the LLM decided to generate their burger website in PHP, JavaScript, Python, Ruby and Perl in successive iterations.

There's this cool new program that the kids are using. It's called Docker. You should check it out.

Re: LLMs as the new high level language

#62

Post by mjr00 »

hackyhacky wrote: post #61
mjr00 wrote: post #58

Earlier quoted context omitted.

Is the LLM paying for hosting in this scenario, too? Is the LLM signing up for the new hosting provider that supports PHP after initially deploying to github pages? Feels like the non-programmer is going to care a little bit about paying for 5 different hosting providers because the LLM decided to generate their burger website in PHP, JavaScript, Python, Ruby and Perl in successive iterations.

> Is the LLM paying for hosting in this scenario, too? Is the LLM signing up for the new hosting provider that supports PHP after initially deploying to github pages? It's an implementation detail. The user doesn't care. OpenClaw can buy its own hosting if you ask it to. > Feels like the non-programmer is going to care a little bit about paying for 5 different hosting providers because the LLM decided to generate the…

How's the non-programmer going to tell the LLM to use Docker? They don't know what Docker is.

How do you guarantee that the prompt "make me a burger website" results in a Docker container?

Re: LLMs as the new high level language

#63

Post by toprerules »

mjr00 wrote: post #54
toprerules wrote: post #48

Earlier quoted context omitted.

Same situation as when an engineer can't figure something out, they translate the problem into human terms for a product person, and the product person makes a high level decision that allows working around the problem.

Uh that's not what engineers do; do you not have any software development experience, or rather any outside of vibe coding? That would explain your perspective. (for context I am 15+ yr experience former FAANG dev) I don't meant this to sound inflammatory or anything; it's just that the idea that when a developer encounters a difficult bug they would go ask for help from the product manager of all people is so incred…

Staff engineer (also at FAANG), so yes, I have at least comparable experience. I'm not trying to summarize every level of SWE in a few sentences. The point is that AI's infallibility is no different than human infallibility. You may fire a human for a mistake, but it won't solve the business problems they may have created, so I believe the accountability argument is bogus. You can hold the next layer up accountable. The new models are startling good at direction setting, technical to product translation, and providing leadership guidance on technical matters and providing multiple routes for roadblocks.

We're starting to see engineers running into bugs and roadblocks feed input into AI and not only root causing the problem, but suggesting and implementing the fix and taking it into review.

Re: LLMs as the new high level language

#64

Post by mjr00 »

toprerules wrote: post #63
mjr00 wrote: post #54

Earlier quoted context omitted.

Uh that's not what engineers do; do you not have any software development experience, or rather any outside of vibe coding? That would explain your perspective. (for context I am 15+ yr experience former FAANG dev) I don't meant this to sound inflammatory or anything; it's just that the idea that when a developer encounters a difficult bug they would go ask for help from the product manager of all people is so incred…

Staff engineer (also at FAANG), so yes, I have at least comparable experience. I'm not trying to summarize every level of SWE in a few sentences. The point is that AI's infallibility is no different than human infallibility. You may fire a human for a mistake, but it won't solve the business problems they may have created, so I believe the accountability argument is bogus. You can hold the next layer up accountable.…

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?

Re: LLMs as the new high level language

#65

Post by Retric »

hackyhacky wrote: post #57
Retric wrote: post #45

Earlier quoted context omitted.

Optimization level, target architecture, etc are just information fed to the compiler. If it’s still nondeterministic with everything kept the same your compiler is broken.

You're missing the point. I'm not saying that compilers are nondeterminitsic or that LLMs are deterministic. I'm saying that it doesn't matter. No one cares about deterministic results except programmers. The non-technical user who will make software in the future just knows that he gets what he asked for.

Systems randomly failing is of significant concern to non programmers, that’s inherent to the non-deterministic nature of LLM’s.

I can send specific LLM output to QA, I can’t ask QA to validate that this prompt will always produce bug free code even for future versions of the AI.

Re: LLMs as the new high level language

#66

Post by hackyhacky »

Retric wrote: post #65
hackyhacky wrote: post #57

Earlier quoted context omitted.

You're missing the point. I'm not saying that compilers are nondeterminitsic or that LLMs are deterministic. I'm saying that it doesn't matter. No one cares about deterministic results except programmers. The non-technical user who will make software in the future just knows that he gets what he asked for.

Systems randomly failing is of significant concern to non programmers, that’s inherent to the non-deterministic nature of LLM’s. I can send specific LLM output to QA, I can’t ask QA to validate that this prompt will always produce bug free code even for future versions of the AI.

Huh? No.

The output of the LLM is nondeterministic, meaning that the same input to the LLM will result in different output from the LLM.

That has nothing to do with weather the code itself is deterministic. If the LLM produces non-deterministic code, that's a bug, which hopefully will be caught by another sub-agent before production. But there's no reason to assume that programs created by LLMs are non-deterministic just because the LLMs themselves are. After all, humans are non-deterministic.

> I can send specific LLM output to QA, I can’t ask QA to validate that this prompt will always produce bug free code even for future versions of the AI.

This is a crazy scenario that does not correspond to how anyone uses LLMs.

Re: LLMs as the new high level language

#67

Post by hackyhacky »

mjr00 wrote: post #62
hackyhacky wrote: post #61

Earlier quoted context omitted.

> Is the LLM paying for hosting in this scenario, too? Is the LLM signing up for the new hosting provider that supports PHP after initially deploying to github pages? It's an implementation detail. The user doesn't care. OpenClaw can buy its own hosting if you ask it to. > Feels like the non-programmer is going to care a little bit about paying for 5 different hosting providers because the LLM decided to generate the…

How's the non-programmer going to tell the LLM to use Docker? They don't know what Docker is. How do you guarantee that the prompt "make me a burger website" results in a Docker container?

> How's the non-programmer going to tell the LLM to use Docker? They don't know what Docker is.

At this point, I think you are intentionally missing the point.

The non-programmer doesn't need to know about Docker, or race conditions, or memory leaks, or virtual functions. The programmer says "make me a web site" and the LLM figures it out. It will use an appropriate language and appropriate libraries. If appropriate, it will use Docker, and if not, it won't. If the non-programmer wants to change hosting, he can say so, and the LLM will change the hosting.

The level of abstraction goes up. The details that we've spent our lives thinking about are no longer relevant.

It's really not that complicated.

Re: LLMs as the new high level language

#68

Post by mjr00 »

hackyhacky wrote: post #67
mjr00 wrote: post #62

Earlier quoted context omitted.

How's the non-programmer going to tell the LLM to use Docker? They don't know what Docker is. How do you guarantee that the prompt "make me a burger website" results in a Docker container?

> How's the non-programmer going to tell the LLM to use Docker? They don't know what Docker is. At this point, I think you are intentionally missing the point. The non-programmer doesn't need to know about Docker, or race conditions, or memory leaks, or virtual functions. The programmer says "make me a web site" and the LLM figures it out. It will use an appropriate language and appropriate libraries. If appropriate,…

How does the non-programmer know about hosting? They just want a burger site. What's hosting? Is that like Facebook?

To maybe get out of this loop: your entire thesis is that nonfunctional requirements don't matter, which is a silly assertion. Anyone who has done any kind of software development work knows that nonfunctional requirements are important, which is why they exist in the first place.

Re: LLMs as the new high level language

#69

Post by Retric »

hackyhacky wrote: post #66
Retric wrote: post #65

Earlier quoted context omitted.

Systems randomly failing is of significant concern to non programmers, that’s inherent to the non-deterministic nature of LLM’s. I can send specific LLM output to QA, I can’t ask QA to validate that this prompt will always produce bug free code even for future versions of the AI.

Huh? No. The output of the LLM is nondeterministic, meaning that the same input to the LLM will result in different output from the LLM . That has nothing to do with weather the code itself is deterministic. If the LLM produces non-deterministic code, that's a bug, which hopefully will be caught by another sub-agent before production. But there's no reason to assume that programs created by LLMs are non-deterministic…

I agree it’s nonsense.

That we agree it’s nonsense means we agree that using LLM prompts as a high level language is nonsense.

Re: LLMs as the new high level language

#70

Post by toprerules »

mjr00 wrote: post #64
toprerules wrote: post #63

Earlier quoted context omitted.

Staff engineer (also at FAANG), so yes, I have at least comparable experience. I'm not trying to summarize every level of SWE in a few sentences. The point is that AI's infallibility is no different than human infallibility. You may fire a human for a mistake, but it won't solve the business problems they may have created, so I believe the accountability argument is bogus. You can hold the next layer up accountable.…

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.
Post reply on HN