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

Cloudlflare builds OAuth with Claude and publishes all the prompts

github.com

Post reply on HN
Print view View original

541–550 of 552 posts

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#541

Post by nipah »

boruto wrote: post #381
otabdeveloper4 wrote: post #379

Earlier quoted context omitted.

> Still saves a lot of time vs typing everything from scratch No it doesn't. Typing speed is never the bottleneck for an expert. As an offline database of Google-tier knowledge, LLM's are useful. Though current LLM tech is half-baked, we need: a) Cheap commodity hardware for running your own models locally. (And by "locally" I mean separate dedicated devices, not something that fights over your desktop's or laptop's…

I realize I procrastinate less when using LLM to write code which I know I could write.

Amazing, because I realized I procrastinate MORE when using LLM to write code which I know I could write. And not only that, I feel I'm losing the ability to do the coding myself and solve the problems myself when delegating this to the AI. Which is why no one should base their own decisions for life, like using or not using an LLM, on some random story from the internet.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#542

Post by nipah »

brailsafe wrote: post #392
otabdeveloper4 wrote: post #379

Earlier quoted context omitted.

> Still saves a lot of time vs typing everything from scratch No it doesn't. Typing speed is never the bottleneck for an expert. As an offline database of Google-tier knowledge, LLM's are useful. Though current LLM tech is half-baked, we need: a) Cheap commodity hardware for running your own models locally. (And by "locally" I mean separate dedicated devices, not something that fights over your desktop's or laptop's…

> No it doesn't. Typing speed is never the bottleneck for an expert How could that possibly be true!? Seems like it'd be the same as suggesting being constrained to analog writing utensils wouldn't bottleneck the process of publishing a book or research paper. At the very least such a statement implies that people with ADHD can't be experts.

Now you are just being silly with your comparisons. There is no analogy between those things: * the difference between handwritting a book and typing is the extreme pain you would feel in your hands versus being able to write more in the same time without it * the difference between typing and using your voice could be of a similar magnitude for someone with problems in their hands * the difference between any of those writing methods and using an AI to do it for you, is that you are abstracting YOURSELF from the equation, not the method of writing. It's not analogous, not even from a mountain of distance far. You are not less "bottlenecked" because you don't need to write the thing yourself, you are just not producing it at all, it's more analogous to you guiding the hands of another person with vague instructions, using of their own expressivity to make your book for you, then claiming it was you who wrote it. It's not a bottleneck question, it was never a bottleneck question, and this is the case because code IS the writing, it IS the problem solving area where you need to put your mind to work, not writing a prompt, but coding in a specific and well defined formal syntax.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#543

Post by nipah »

fc417fc802 wrote: post #428
brailsafe wrote: post #390

Earlier quoted context omitted.

> I really don't agree with the idea that expert time would just be spent typing, and I'd be really surprised if that's the common sentiment around here. They didn't suggest that at all, they merely suggested that the component of the expert's work that would otherwise be spent typing can be saved, while the rest of their utility comes from intense scrutiny, problem solving, decision making about what to build and wh…

It's not just time spent typing. Figuring out what needs to be typed can be both draining and time consuming. It's often (but not always) much easier to review someone else's solution to the problem than it is to solve it from scratch on your own. Oddly enough security critical flows are likely to be one of the few exceptions because catching subtle reasoning errors that won't trip any unit tests when reviewing code…

> It's not just time spent typing. Figuring out what needs to be typed can be both draining and time consuming. It's often (but not always) much easier to review someone else's solution to the problem than it is to solve it from scratch on your own.

This is EXTREMELY false. When you write the code you [remember] it, it's fresh in your head, you [know] what it is doing and exactly what it's supposed to do. This is why debugging a codebase you didn't wrote is harder than one you wrote, if a bug happens you know exactly the spots it could be happening at and you can easily go and check them.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#544

Post by nipah »

fastball wrote: post #509
shaky-carrousel wrote: post #454

Earlier quoted context omitted.

Hundreds of lines that you have to carefully read and understand.

Are you not doing that already? I go line-by-line through the code that I wrote (in my git client) before I stage+commit it.

You read at the same speed line-by-line your code when you are in your git client?

You are doing something wrong. I go line-by-line through my code like 7x faster than I would do it for someone's else code, because I know what I wrote, my own intentions, my flow of coding and all of those details. I can just look at it en passant, while with AI code I need to carefully review every single detail and the connection between them to approve it.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#545

Post by nipah »

kentonv wrote: post #470
autoexec wrote: post #468

Earlier quoted context omitted.

> I thoughts LLMs were glorified Markov chain generators that didn't actually understand code and couldn't produce anything novel. How novel is a OAuth provider library for cloudflare workers? I wouldn't be surprised if it'd been trained on multiple examples.

I'm not aware of any other OAuth provider libraries for Workers. Plenty of clients, but not providers -- implementing the provider side is not that common, historically. See my other comment: https://news.ycombinator.com/item?id=44164204

Novelness is not a characteristic of interpolation, tho, it's about extrapolation. If you have plenty of clients and plenty of related stuff to the provider side, even if on on auth, then it could be considerably trivial for the LLM to interpolate on that field.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#546

Post by nipah »

kentonv wrote: post #105
paxys wrote: post #10

This is exactly the direction I expect AI-assisted coding to go in. Not software engineers being kicked out and some business person pressing a few buttons to have a fully functional app (as is playing out in a lot of fantasies on LinkedIn & X), but rather experienced engineers using AI to generate bits of code and then meticulously reviewing and testing them. The million dollar (perhaps literally) question is – coul…

It took me a few days to build the library with AI. I estimate it would have taken a few weeks, maybe months to write by hand. That said, this is a pretty ideal use case: implementing a well-known standard on a well-known platform with a clear API spec. In my attempts to make changes to the Workers Runtime itself using AI, I've generally not felt like it saved much time. Though, people who don't know the codebase as…

Your estimation maybe right, but maybe also there is a point on why it is right: https://neilmadden.blog/2025/06/06/a-look-at-cloudflares-ai-...

Maybe because (and I'm quoting that article) it is still lacking in what it should have that you managed to accomplish this task in "few days" instead of "a few weeks, maybe months".

Maybe the bottleneck was not your typing speed, but the [specific knowledge] to build that system. Because if you know something well enough, you can build it way faster, like rebuilding something from scratch, you will be faster as you already know the paths. In which case, my question would be: would not be writing this as fast, or maybe at least more secure and reasonable, if you had the complete knowledge of the system first.

Because contrary to LLMs, humans can actually improve and learn when they do things, and they don't whey they don't do things. Not knowing the code to the full extent is worth the time "gained" by using the LLM to write it?

I think it's very hard to estimate those other aspects of the thing.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#547

Post by nipah »

ookblah wrote: post #118

AI critics always have to make strawmen arguments about how there has to be a human in the loop to "fix" things when that's never been the argument AI proponents ever make (at least those who deal with it day to day). This will only get better with time. AI can frequently one-shot throwaway scripts that I need get things done. For actual features I typically start and have it go thru the initial slog and then finish…

> This will only get better with time.

Prove it.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#548

Post by nipah »

cyberax wrote: post #332

I looked through the source code, and it looks reasonable. The code is well-commented (even _over_ commented a bit). There are probably around ~700 meaningful lines of pure code. So this should be about 2 weeks of work for a good developer. This is without considering the tests. And OAuth is not particularly hard to implement, I did that a bunch of times (for server and the client side). It's well-specified and so it…

700 lines of code is 2 weeks of work for a good developer? My friend, I wrote 350 lines of executable code (excluding boilerplate) in a morning (4AM to like 9AM, maybe a bit more) to make a test with voxel octrees like yesterday. There's no reason it would take "2 weeks of work for a good developer" to write 700. What takes times in those projects is the research, if you already have this fresh in your head it should not take more than 3 days to make something very simple but reasonable, and a week at max to make something good (not perfect, but good).

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#549

Post by nipah »

kentonv wrote: post #121
noodletheworld wrote: post #114

Earlier quoted context omitted.

If you had written it by hand would the verification process been as time consuming? i.e. overall including the time spent verifying that it was correct, do you consider it a net win?

I was already including my own time spent verifying the output, which I mostly did right away as the code was being generated (approving or rejecting each edit). And the separate security review would have been required either way. So yes, it saved time.

Did you wrote it from scratch to compare? There's an old motto devs use all the time, you know. Measure first, don't guess. How do you know it would not have took you the same time or less to write the program if it was you? Or if for example, if you were using the AI to write the boilerplate for you while you focused on the core of coding? Or using it as a tab completor assistant instead of it being an agent? Saying it saved you time is easy when you don't have the data to back it up, it's easier than thinking that maybe, maybe this was not that good of an use of your time.

Re: Cloudlflare builds OAuth with Claude and publishes all the prompts

#550

Post by nipah »

TeMPOraL wrote: post #79
teaearlgraycold wrote: post #69

> Every line was thoroughly reviewed and cross-referenced with relevant RFCs, by security experts with previous experience with those RFCs. This sounds like coding but slower

The point was validating a hypothesis. That is the validation part.

You don't validate an hypothesis without testing counterfactuals, tho.
Post reply on HN