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

161–170 of 291 posts

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

#161

Post by tptacek »

kiitos wrote: post #152
tptacek wrote: post #119

Earlier quoted context omitted.

When you say "the LLM can easily hallucinate code that will satisfy the compiler but still fail the actual intent of the user", all you are saying is that the code will have bugs. My code has bugs. So does yours. You don't get to use the fancy word "hallucination" for reasonable-looking, readable code that compiles and lints but has bugs. I think at this point our respective points have been made, and we can wrap it…

> When you say "the LLM can easily hallucinate code that will satisfy the compiler but still fail the actual intent of the user", all you are saying is that the code will have bugs. My code has bugs. So does yours. You don't get to use the fancy word "hallucination" for reasonable-looking, readable code that compiles and lints but has bugs. There is an obvious and categorical difference between the "bugs" that an LLM…

They obviously are.

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

#162

Post by tptacek »

skydhash wrote: post #136
tptacek wrote: post #123

Earlier quoted context omitted.

Just checking off the list of things you've determined to be irrelevant. Compiler? Nope. Linter? Nope. Test suite? Nope. How about TLA+ specifications?

TLA+ specs don’t verify code. They verify design. Such design can be expressed in whatever, including pseudocode (think algorithms notation in textbooks). Then you write the TLA specs that will judge if invariants are truly respected. Once you’re sure of the design, you can go and implement it, but there’s no hard constraints like a type system.

At what level of formal methods verification does the argument against AI-generated code fall apart? My expectation is that the answer is "never".

The subtext is pretty obvious, I think: that standards, on message boards, are being set for LLM-generated code that are ludicrously higher than would be set for people-generated code.

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

#163

Post by keybored »

lcnPylGDnU4H9OF wrote: post #142
keybored wrote: post #80

Earlier quoted context omitted.

Radicalized? Going with the flow and wishes of the people who are driving AI is the opposite of that. To have their minds changed drastically, sure..

> very different from the usual or traditional https://www.merriam-webster.com/dictionary/radical Deciding that AI is going nowhere to suddenly deciding that coding agents are how they will work going forward is a radical change. That is what they meant.

Did you miss my second paragraph?

https://www.merriam-webster.com/dictionary/paragraph

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

#164

Post by grey-area »

latexr wrote: post #111
grey-area wrote: post #107

Earlier quoted context omitted.

Very few people use n dashes in internet writing as opposed to dashes as they are not available on the default keyboard.

That’s not true at all. Apple’s OS by default have smart punctuation enabled and convert -- (two hyphens) into — (“em-dash”; not an “en-dash”, which has a different purpose), " " (dumb quotes) into “ ” (smart quotes), and so forth. Furthermore, on macOS there are simple key combinations (e.g. with ⌥) to make all sort of smart punctuation even if you don’t have the feature enabled by default, and on iOS you can long p…

So we’ve established the default is a hyphen, not an em dash.

You can certainly select an em dash but most don’t know what it means and don’t use it.

It’s certainly not infallible proof but multiple uses of it in comments online (vs published material or newspapers) are very unusual, so I think it’s an interesting indicator. I completely agree it is common in some texts, usually ones from publishing houses with style guides but also people who know about writing or typography.

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

#165

Post by grey-area »

thoroughburro wrote: post #122
grey-area wrote: post #107

Earlier quoted context omitted.

Very few people use n dashes in internet writing as opposed to dashes as they are not available on the default keyboard.

On the “default keyboard” of most people (a phone), you just long-press hyphen to choose any dash length.

But who does? Not many.

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

#166

Post by cavisne »

IncreasePosts wrote: post #18

I asked this in the other thread (no response, but I was a bit late) How does anyone using AI like this have confidence that they aren't unintentionally plagiarizing code and violating the terms of whatever license it was released under? For random personal projects I don't see it mattering that much. But if a large corp is releasing code like this, one would hope they've done some due diligence that they have to jus…

Some API's (Gemini at least) run a search on their outputs to see if the model is reciting data from training.

So for direct copies like what you are talking about that would be picked up.

For copying concepts from other libraries, seems like a problem with or without LLM's.

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

#167

Post by mpalmer »

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.

The sentence itself is a smeLLM. Grandiose pronouncements aren't a bot exclusive, but man do they love making them, especially about creative paradigms and dynamics

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

#168

Post by david-gpu »

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…

Please tell us we company you are working for so that we don't send our resumes there.

Jokes aside, I have worked in projects where auto-generating code was the solution that was chosen and it's always been 100% auto-generated, essentially at compilation time. Any hand-coded stuff needed to handle corner cases or glue pieces together was kept outside of the code generator.

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

#169

Post by croes »

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…

You couldn’t even tell in advance if the prompt produces code at all.

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

#170

Post by tptacek »

BurritoKing wrote: post #147
kevingadd wrote: post #47

Earlier quoted context omitted.

I think it makes sense that GP is skeptical of this article considering it contains things like: > this tool is improving itself, learning from every interaction which seem to indicate a fundamental misunderstanding of how modern LLMs work: the 'improving' happens by humans training/refining existing models offline to create new models, and the 'learning' is just filling the context window with more stuff, not enhanc…

When you consider the "tool" as more than just the LLM model, but the stuff wrapped around calling that model then I feel like you can make a good argument it's improving when it keeps context in a file on disk and constantly updates and edits that file as you work throguh the project. I do this routinely for large initiatives I'm kicking off through Claude Code - it writes a long detailed plan into a file and as we…

I would love to hear more about this workflow.
Post reply on HN