Live data from Hacker News

Cloudlflare builds OAuth with Claude and publishes all the prompts

github.com

481–490 of 552 posts

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

#481

The commits are revealing. Look at this one: > Ask Claude to remove the "backup" encryption key. Clearly it is still important to security-review Claude's code! > prompt: I noticed you are storing a "backup" of the encryption key as `encryptionKeyJwk`. Doesn't this backup defeat the end-to-end encryption, because the key is available in the grant record without needing any token to unwrap it? I don’t think a non-expe…

Yeah I was disappointed in that one. I hate to say, though, but I have reviewed a lot of human code in my time, and I've definitely caught many humans making similar-magnitude mistakes. :/

Most interesting aspect of this is it likely learned this pattern from human-written code!

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

#482
Reading the authors comments on the github page I can relate. Over this paast weekend I attempted to use copilot to write some code for a home project and expected it to be terrible, like the last time I tried.

Except, this time it wasn't. It got most things right first time, and fixed things I asked it to.

I was pleasantly surprised.

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

#484
post #401

Earlier quoted context omitted.

It was clearly rhetorical

Even if it were, which I disagree, treating it was though it were a plain sincere question instead of rhetorical would lead to better discussions.

Yeah I was a bit snarky, my bad. I was also genuinely curious though, as it did seem like an odd question that probably had a point behind it.

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

#485

Fascinating It's like cooking with a toddler The end result has a lower quality than your own potential, it takes more time to be producted, and it is harder too because you always need to supervise and correct what's done

> it takes more time to be producted, and it is harder too because you always need to supervise and correct what's done

This is hogwash, the lead dev in charge of this has commented elsewhere that he's saved inordinate amounts of time. He mentioned that he gets about a day a week to code and produced this in under a month, which under those circumstances would've been impossible without LLM assistance.

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

#486
post #159

Earlier quoted context omitted.

Maybe it's contrarian, maybe it's not, but I don't think Chat UIs are well suited for software engineering/programming at all, we need something completely different. Being able to branch conversations and such would be useful, but probably not for the way I do software. Besides, I'm rarely beyond 3 messages (1 system, 1 user, 1 assistant) in any usage of the chat UIs. Maybe it's more useful to people with different…

I don't see how you'd avoid using chat if you need the bot to work on some bug end-to-end. I usually have many rounds in a chat session, first asking it to identify the overall approach, reviewing and approving that, then one or more rounds for coding, and several more to request edits as needed. If you only ever ask it for trivial changes that don't require past context to make sense, then chat is indeed overkill. B…

Yeah, I'd agree you want to iterate, but I'm not sure the UX of "Log of messages, where some of yours, some are tool calls, others are the assistant" and the workflow of "Add more messages into the log of messages"/"Change existing messages" is the right broad UX for this type of work.

I'm sorry I can't substantiate it more than that, as my own head is still trying to wrap itself around what I think is needed instead. Still, sounds very "fluffy" even when I read it back myself.

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

#487
post #446

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?

Some may have a better answer, but I often compare with tools like OpenAPI and AsyncAPI generators where HTTP/AMQP/etc code can be generated for servers, clients and extended documentation viewers.

The trade off here would be that you must create the spec file (and customize the template files where needed) which drives the codegen, in exchange for explicit control over deterministic output. So there’s more typing but potentially less cognitive overhead with reviewing a bunch of LLM output.

For this use case I find the explicit codegen UX preferable to inspecting what the LLM decided to do with my human-language prompt, if attempting to have the LLM directly code the library/executable source (as opposed to asking it to create the generator, template or API spec).

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

#488

Earlier quoted context omitted.

A prompt can be as little as a sentence to write hundreds of lines of code.

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

You also have to do that with code you write without LLM assistance.

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

#489

Earlier quoted context omitted.

> But what if you only need 2 kentonv's instead of 20 at the end? Do you assume we'll find enough new tasks that will occupy the other 18? I think that's the question. This is likely where all this will end up. I have doubts that AI will replace all engineers, but I have no doubt in my mind that we'll certainly need a lot less engineers. A not so dissimilar thing happened in the sysadmin world (my career) when everyt…

I think there's a huge huge space of software to build that isn't being touched today because it's not cost-effective to have an engineer build them. But if the time it takes an engineer to build any one thing goes down, now there are a lot more things that are cost effective. Consider niche use cases. Every company tends to have custom processes and workflows. Think about being an accountant at one company vs. anoth…

I work for SMEs as a consulting CTO, and this is exactly where I see things going in this domain. I can take care of workloads that would've been prohibitively expensive in the past. In the case of SMEs, this may cover critical problems whose resolution can unlock new levels of growth. LLMs can be an absolute boon for them, and I'm fairly optimistic about being able to capitalize on the opportunity.

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

#490
post #419

Earlier quoted context omitted.

I tend to disagree, but I don't know what my disagreement means for the future of being able to use AI when writing software. This workers-oauth-provider project is 1200 lines of code. An expert should be able to write that on the scale of an hour. The main value I've gotten out of AI writing software comes from the two extremes; not from the middle-ground you present. Vibe coding can be great and seriously productiv…

> An expert should be able to write that on the scale of an hour. An expert in oauth, perhaps. Not your typical expert dev who doesn't specialize in auth but rather in whatever he's using the auth for. Navigating those sorts of standards is extremely time consuming.

Maybe, but also: Cloudflare is one of like fifteen organizations on the planet writing code like this. The vast majority of The Rest Of Us will just consume code like this, which companies like Cloudflare, Auth0, etc write. That tends to be the nature of highly-specialized highly-domain-specific code. Cloudflare employs those mythical Oauth experts you talk about.
Post reply on HN