Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I read all of Cloudflare's Claude-generated commits

maxemitchell.com

Post reply on HN
Print view View original

81–90 of 291 posts

Re: I read all of Cloudflare's Claude-generated commits

#81

Post by kiitos »

tptacek wrote: post #58
kiitos wrote: post #57

Earlier quoted context omitted.

What on earth are you talking about?? If the LLM hallucinates, then the code it produces is wrong. That wrong code isn't obviously or programmatically determinable as wrong, the agent has no way to figure out that it's wrong, it's not as if the LLM produces at the same time tests that identify that hallucinated code as being wrong. The only way that this wrong code can be identified as wrong is by the human user "loo…

No, what's happening here is we're talking past each other. An agent lints and compiles code . The LLM is stochastic and unreliable. The agent is ~200 lines of Python code that checks the exit code of the compiler and relays it back to the LLM. You can easily fool an LLM. You can't fool the compiler. I didn't say anything about whether code needs to be reviewed line-by-line by humans. I review LLM code line-by-line.…

> If the LLM hallucinates, then the code it produces is wrong. That wrong code isn't obviously or programmatically determinable as wrong, the agent has no way to figure out that it's wrong, it's not as if the LLM produces at the same time tests that identify that hallucinated code as being wrong. The only way that this wrong code can be identified as wrong is by the human user "looking closely" and figuring out that it is wrong

The LLM can easily hallucinate code that will satisfy the agent and the compiler but will still fail the actual intent of the user.

> I review LLM code line-by-line. Lots of code that compiles clean is nonetheless horrible.

Indeed most code that LLMs generate compiles clean and is nevertheless horrible! I'm happy that you recognize this truth, but the fact that you review that LLM-generated code line-by-line makes you an extraordinary exception vs. the normal user, who generates LLM code and absolutely does not review it line-by-line.

> But none of [the LLM generated code] includes hallucinated API calls.

Hallucinated API calls are just one of many many possible kinds of hallucinated code that an LLM can generate, by no means does "hallucinated code" describe only "hallucinated API calls" -- !

Re: I read all of Cloudflare's Claude-generated commits

#82

Post by diggan »

mschild wrote: post #61
gizmo686 wrote: post #59

Earlier quoted context omitted.

My work has involved a project that is almost entirely generated code for over a decade. Not AI generated, the actual work of the project is in creating the code generator. One of the things we learned very quickly was that having generated source code in the same repository as actual source code was not sustainable. The nature of reviewing changes is just too different between them. Another thing we learned very qui…

> One of the things we learned very quickly was that having generated source code in the same repository as actual source code was not sustainable. Keeping a repository with the prompts, or other commands separate is fine, but not committing the generated code at all I find questionable at best.

If you can 100% reproduce the same generated code from the same prompts, even 5 years later, given the same versions and everything then I'd say "Sure, go ahead and don't saved the generated code, we can always regenerate it". As someone who spent some time in frontend development, we've been doing it like that for a long time with (MB+) generated code, keeping it in scm just isn't feasible long-term.

But given this is about LLMs, which people tend to run with temperature>0, this is unlikely to be true, so then I'd really urge anyone to actually store the results (somewhere, maybe not in scm specifically) as otherwise you won't have any idea about what the code was in the future.

Re: I read all of Cloudflare's Claude-generated commits

#83

Post by keybored »

dcre wrote: post #62
thorum wrote: post #23

Humorous that this article has a strong AI writing smell - the author should publish the prompts they used!

I don’t like to accuse, and the article is fine overall, but this stinks: “This transparency transforms git history from a record of changes into a record of intent, creating a new form of documentation that bridges human reasoning and machine implementation.”

> I don’t like to accuse, and the article is fine overall, but this stinks:

Now consider your reasonable instinct to not accuse other people coupled with the possibility setting AI lose with “write a positive article about AI where you have some paragraphs about the current limitations based on this link. write like you are just following the evidence.” Meanwhile we are supposed to sit here and weigh every word.

This reminds to write a prompt for a blogpost. How AI could be used for making personal-looking tech-guy who meditates and runs websites. (Do we have the technology? Yes we do)

Re: I read all of Cloudflare's Claude-generated commits

#84

Post by cimi_ »

gizmo686 wrote: post #59
SrslyJosh wrote: post #5

> Reading through these commits sparked an idea: what if we treated prompts as the actual source code? Imagine version control systems where you commit the prompts used to generate features rather than the resulting implementation. Please god, no, never do this. For one thing, why would you not commit the generated source code when storage is essentially free? That seems insane for multiple reasons. > When models ine…

My work has involved a project that is almost entirely generated code for over a decade. Not AI generated, the actual work of the project is in creating the code generator. One of the things we learned very quickly was that having generated source code in the same repository as actual source code was not sustainable. The nature of reviewing changes is just too different between them. Another thing we learned very qui…

I will guess that you are generating orders of magnitude more lines of code with your software than people do when building projects with LLMs - if this is true I don't think the analogy holds.

Re: I read all of Cloudflare's Claude-generated commits

#85

Post by ZephyrBlu »

dcre wrote: post #62
thorum wrote: post #23

Humorous that this article has a strong AI writing smell - the author should publish the prompts they used!

I don’t like to accuse, and the article is fine overall, but this stinks: “This transparency transforms git history from a record of changes into a record of intent, creating a new form of documentation that bridges human reasoning and machine implementation.”

Also: "This OAuth library represents something larger than a technical milestone—it's evidence of a new creative dynamic emerging"

Em-dash baby.

Re: I read all of Cloudflare's Claude-generated commits

#86

Post by latexr »

declan_roberts wrote: post #22

These posts are funny to me because prompt engineers point at them as evidence of the fast-approaching software engineer obsolescence but the years of experience in software engineering necessary to even guide an AI in this way is very high. The reason he keeps adjusting the prompts is because he knows how to program. He knows what it should look like. It just blurs the line between engineer and tool.

> It just blurs the line between engineer and tool.

I realise you meant it as “the engineer and their tool blend together”, but I read it like a funny insult: “that guy likes to think of himself as an engineer, but he’s a complete tool”.

Re: I read all of Cloudflare's Claude-generated commits

#87

Post by latexr »

ZephyrBlu wrote: post #85
dcre wrote: post #62

Earlier quoted context omitted.

I don’t like to accuse, and the article is fine overall, but this stinks: “This transparency transforms git history from a record of changes into a record of intent, creating a new form of documentation that bridges human reasoning and machine implementation.”

Also: " This OAuth library represents something larger than a technical milestone—it's evidence of a new creative dynamic emerging " Em-dash baby.

Can we please stop using the em-dash as a metric to “detect” LLM writing? It’s lazy and wrong. Plenty of people use em-dashes, it’s a useful punctuation mark. If humans didn’t use them, they wouldn’t be in the LLM training data.

There are better clues, like the kind of vague pretentious babble bad marketers use to make their products and ideas seem more profound than they are. It’s a type of bad writing which looks grandiose but is ultimately meaningless and that LLMs heavily pick up on.

Re: I read all of Cloudflare's Claude-generated commits

#88

Post by brador »

Many of you are failing to conprehend the potential scale of AI generated codebases.

Take note - there is no limit. Every feature you or the AI can prompt can be generated.

Imagine if you were immortal and given unlimited storage. Imagine what you could create.

That’s a prompt away.

Even now you’re still restricting your thinking to the old ways.

Re: I read all of Cloudflare's Claude-generated commits

#89

Post by visarga »

SrslyJosh wrote: post #5

> Reading through these commits sparked an idea: what if we treated prompts as the actual source code? Imagine version control systems where you commit the prompts used to generate features rather than the resulting implementation. Please god, no, never do this. For one thing, why would you not commit the generated source code when storage is essentially free? That seems insane for multiple reasons. > When models ine…

The idea is good, but we should commit both documentation and tests. They allow regenerating the code at will.

Re: I read all of Cloudflare's Claude-generated commits

#90

Post by visarga »

declan_roberts wrote: post #22

These posts are funny to me because prompt engineers point at them as evidence of the fast-approaching software engineer obsolescence but the years of experience in software engineering necessary to even guide an AI in this way is very high. The reason he keeps adjusting the prompts is because he knows how to program. He knows what it should look like. It just blurs the line between engineer and tool.

> prompt engineers point at them as evidence of the fast-approaching software engineer obsolescence

Maybe journalists and bloggers angling for attention do it, prompt engineers are too aware of the limitations of prompting to do that.

Post reply on HN