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

511–520 of 552 posts

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

#511

Post by s900mhz »

oblio wrote: post #445
thisissomething wrote: post #409

Earlier quoted context omitted.

Completely agree with you. I was working on the front-end of an application and I prompted Claude the following: "The endpoint /foo/bar is returning the json below ##json goes here##, show this as cards inside the component FooBaz following the existing design system". In less than 5 minutes Claude created code that: - encapsulated the api call - modeled the api response using Typescript - created a re-usable and res…

The thing is... does your code end there? Would you put that code in production without a deep analysis of what Claude did?

I’m not who you replied to but I keep functions small and testable paired with unit tests with a healthy mix of happy/sad path.

Afterwards I make sure the LLM passes all the tests before I spend my time to review the code.

I find this process keeps the iterations count low for review -> prompt -> review.

I personally love writing code with an LLM. I’m a sloppy typist but love programming. I find it’s a great burnout prevention.

For context: node.js development/React (a very LLM friendly stack.)

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

#512

Post by gcr »

This library has some pretty bad security bugs. For example, the author forgot to check that redirect_uri — matches one of the URLs listed during client registration.

The CVE is uncharacteristically scornful: https://nvd.nist.gov/vuln/detail/cve-2025-4143

I’m glad this was patched, but it is a bit worrying for something “not vibe coded” tbh

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

#513

Post by rienbdj »

nijave wrote: post #446
Culonavirus wrote: post #403

Earlier quoted context omitted.

Depends on what you're doing. For example when you're writing something like React components and using something like Tailwind for styling, I find the speedup is close to 10X.

Isn't there some way to speed up with codegen besides using LLMs?

You can require less code by using a more expressive programming language.

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

#514

Post by ath92 »

basfo wrote: post #389
petersellers wrote: post #359

Earlier quoted context omitted.

> In your own words, a project that would take 5-10 engineers is now feasible to be tackled with 1 or 2. Your own words. That statement != lower demand for software engineers. If a firm needs to perform project X that previously cost 10 engineers to do, but they only have the budget for 2, they will not tackle that project. Engineers used = 0. However, if due to productivity enhancements with AI, the project can now…

> If a firm needs to perform project X that previously cost 10 engineers to do, but they only have the budget for 2, they will not tackle that project. Engineers used = 0. 0 on that Project, but those 2 engineers will still be used on a different Project that needs just 2 Engineers. BUT a company that sees that project as a critical part of the bussines and MUST tackle that project, will only need the 2 engineers in…

But now every firm has access to AI. If a firm that doesn’t fire people but instead simply boosts productivity, they will out compete their competitors. The only way to compete with that firm is to also hire enough employees and give them AI tools.

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

#515

Post by TeMPOraL »

nand_gate wrote: post #224
TeMPOraL wrote: post #101

Earlier quoted context omitted.

It's not. Consider that replacing the only $200k software engineer on the project is different than replacing the third or tenth $200k software engineer on the project. To the extent AI is improving productivity of those engineers, it reduces the need for adding more engineers to that team. That may mean firing some of them, or just not hiring new ones (or fewer of them) as the project expands, as existing ones + AI…

I'm biased but my money's on the end result of AI being fewer engineers per team but also teams as a concept becoming obsolete. Why keep legacy structures, with luxuries like POs or PMs if AI becomes powerful as you say - it'll just be 'one man startups' for better or worse. Any empire-building VP should probably fear the wishful AI future they're praying for!

> it'll just be 'one man startups' for better or worse.

Not necessarily. The reality is, whatever some people can do individually, if they team up, they can do more together. The teams and small startups will remain for now, and so will big companies.

I do imagine however that the internal structure will change. As the AI gets better and able to do more independently, people will shift from pair programming to more of a PM role (this is happening now), and this I imagine will quickly collapse further.

Even today, LLMs seem more suited for project management than doing actual coding - it's just the space in-between that's the problem. I.e. LLMs can code great in the small, and can break down work very well, but keeping the changes consistent and following the plan is where they still struggle. As that gap closes, I'm not really sure how the team composition would look like. But I don't doubt there'd still be teams.

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

#516

Post by sceptic123 »

dkdcio wrote: post #138
sceptic123 wrote: post #70

If you need to be an expert to use AI tools safely, what does that say about AI tools?

Genuinely curious what your point is? Do you know how to use a ventillator? A A timing gun? A tonometer? A keratometer? Can you use all of those in a "production" setting safely without expertise?

To speak to your analogy, I could possibly use a fully automated tonometer (or maybe a defibrillator). The idea being that the tool can guide a non-expert through the required steps.

If I had a point it would be that these tools are currently offered as if they are experts and are taking you through the steps as if they can be trusted. The reality is far from that, and understanding that difference is key to how we approach their use.

Maybe this will change in the future, but right now, you need to be an expert to use AI coding tools, I don't think many people understand that.

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

#517

Post by sceptic123 »

seunosewa wrote: post #182
sceptic123 wrote: post #63

Earlier quoted context omitted.

> as long as it produces the results you expect? But it's more the case of "until it doesn't produce the results you expect" and then what do you do?

Then you teach it. Even humans don't always produce the results we expect.

Have you tried that? It generally doesn't go so well.

In this example there are several commits where you can see they needed to fix the code because they couldn't get (teach) the LLM to generate the required code.

And there's no memory there, you open a new prompt and it's forgotten everything you said previously.

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

#518

Post by sceptic123 »

sceptic123 wrote: post #516
dkdcio wrote: post #138

Earlier quoted context omitted.

Genuinely curious what your point is? Do you know how to use a ventillator? A A timing gun? A tonometer? A keratometer? Can you use all of those in a "production" setting safely without expertise?

To speak to your analogy, I could possibly use a fully automated tonometer (or maybe a defibrillator). The idea being that the tool can guide a non-expert through the required steps. If I had a point it would be that these tools are currently offered as if they are experts and are taking you through the steps as if they can be trusted. The reality is far from that, and understanding that difference is key to how we a…

I think as well, you can be an expert in software development without being an expert in software security. If you rely on a coding assistant in that situation then you run the risk of writing insecure code together.

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

#519

Post by XCSme »

Culonavirus wrote: post #403
XCSme wrote: post #396

Earlier quoted context omitted.

> Still saves a lot of time vs typing everything from scratch. In my experience, it takes longer to debug/instruct the LLM than to write it from scratch.

Depends on what you're doing. For example when you're writing something like React components and using something like Tailwind for styling, I find the speedup is close to 10X.

Scaffolding works fine, for things that are common, and you already have 100x examples on the web. Once you need something more specific, it falls apart and leads to hours of prompting and debugging for something that takes 30 minutes to write from scratch.

Some basic things it fails at:

  * Upgrading the React code-base from Material-UI V4 → V5
  * Implementing a simple header navigation dropdown in HTML/CSS that looks decent and is usable (it kept having bugs with hovering, wrong sizes, padding, responsiveness, duplicated code etc.)
  * Changing anything. About half of the time, it keeps saying "I made those changes", but no changes were made (it happens with all of them, Windsurf, Copilot, etc.).

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

#520

Post by lenglain »

azemetre wrote: post #407
Culonavirus wrote: post #403

Earlier quoted context omitted.

Depends on what you're doing. For example when you're writing something like React components and using something like Tailwind for styling, I find the speedup is close to 10X.

Isn’t this because the LLMs had like a million+ react tutorials/articles/books/repos to train on? I mean I try to use them for svelte or vue and it still recommends react snippets sometimes.

I have had no issues with LLMs trying to force a language on me. I tried the whole snake game test with ChatGPT but Instead of using Python I asked it to use the nodejs bindings for raylib, which is rather unusual.

It did it in no time and no complaints.

Post reply on HN