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

51–60 of 552 posts

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

#51

Post by diggan »

mysterydip wrote: post #46
infinitebattery wrote: post #23

From this commit: https://github.com/cloudflare/workers-oauth-provider/commit/... === "Fix Claude's bug manually. Claude had a bug in the previous commit. I prompted it multiple times to fix the bug but it kept doing the wrong thing. So this change is manually written by a human. I also extended the README to discuss the OAuth 2.1 spec problem." === This is super relatable to my experience trying to use these AI tool…

This to me is why I think these tools don't have actual understanding, and are instead producing emergent output from pooling an incomprehensibly large set of pattern-recognized data.

> these tools don't have actual understanding, and are instead producing emergent output from pooling an incomprehensibly large set of pattern-recognized data

I mean, bypassing the fact that "actual understanding" doesn't have any consensus about what it is, does it matter if it's "actual understanding" or "kind of understanding", or even "barely understanding", as long as it produces the results you expect?

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

#52

Post by paxys »

gokhan wrote: post #45
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…

> Not software engineers being kicked out ... but rather experienced engineers using AI to generate bits of code and then meticulously reviewing and testing them. 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. And the author is implementing a fairly technical project in this case. How about routine L…

Increased productivity means increased opportuntity. There isn't going to be a time (at least not anytime soon) when we can all sit back and say "yup, we have accomplished everything there is to do with software and don't need more engineers".

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

#53

Post by stego-tech »

On the one hand, I would expect LLMs to be able to crank out such code when prompted by skilled engineers who also understand prompting these tools correctly. OAuth isn’t new, has tons of working examples to steal as training data from public projects, and in a variety of existing languages to suit most use cases or needs.

On the other hand, where I remain a skeptic is this constant banging-on that somehow this will translate into entirely new things - research, materials science, economies, inventions, etc - because that requires learning “in real time” from information sources you’re literally generating in that moment, not decades of Stack Overflow responses without context. That has been bandied about for years, with no evidence to show for it beyond specifically cherry-picked examples, often from highly-controlled environments.

I never doubted that, with competent engineers, these tools could be used to generate “new” code from past datasets. What I continue to doubt is the utility of these tools given their immense costs, both environmentally and socially.

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

#54

Post by jes5199 »

diggan wrote: post #35
jes5199 wrote: post #21

I’ve been using Claude (via Cursor) on a greenfield project for the last couple months and my observation is: 1. I am much more productive/effective 2. It’s way more cognitively demanding than writing code the old-fashioned way 3. Even over this short timespan, the tools have improved significantly, amplifying both of the points above

> It’s way more cognitively demanding than writing code the old-fashioned way How are you using it? I've been mainly doing "pair programming" with my own agent (using Devstral as of late) and find the reviewing much easier than it would been to literally type all of the code it produces, at least time wise. I've also tried vibe coding for a bit, and for that I'd agree with you, as you don't have any context if you en…

I’ve tried a bunch of things but now I’m mostly using Cursor in agent mode with Claude Sonnet 4, doing small-ish pull-request-sized prompts. I don’t have to review code as carefully as I did with Claude 3.7

but I’m finding the bottleneck now is architecture design. I end up having these long discussions with chatGPT-o3 about design patterns, sometimes days of thinking, and then relatively quick implementation sessions with Cursor

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

#55

Post by diggan »

_tqr3 wrote: post #49

I’ve tried building a web app with LLMs before. Two of them went in circles—I'd ask them to fix an infinite loop, they’d remove the code for a feature; I’d ask them to add the feature back, they’d bring back the infinite loop, and so on. The third one kept losing context—after just 2–3 messages, it would rebuild the whole thing differently. They’ll probably get better, but for now I can safely say I’ve spent more tim…

Rather than doing that approach which eventually builds up to 10+ messages or more, iterate on your initial prompt and you'll see better results. So if the first prompt correctly fixed the infinite loop, but removed something else, instead of saying "Add that back again", change the initial prompt to include "Don't remove anything else than what's explicitly mentioned" or similar, and you'll either get exactly what you want, or some other issue. Then rinse and repeat until completed.

Eventually you'll build up a somewhat reusable template you can use as a system prompt to guide it exactly how you want.

Basically, you get what you ask for, nothing else and nothing more. If you're unclear, it'll produce unclear outputs, if you didn't mention something, it'll do whatever with that. You have to be really, really explicit about everything.

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

#57

Post by uludag »

mdaniel wrote: post #37
diggan wrote: post #28

Earlier quoted context omitted.

> It may also be wildly out of scope for including in a project's readme The entire point of the repository seems to be to invalidate/validate the thesis if LLMs are good enough to be pair programmers right now. Removing it from the README makes no sense in that context.

I did consider that, but the repo isn't called "kentonv does a yolo" it's straight-up labeled as a provider library for CF workers under Cloudflare's brand Some hair splitting about whether including the Claude stanza is "full disclosure," or "AI advocacy," or just because it's cool Anyway, I mentioned the out of scope because if half the readme is about correct usage of the library, and half is about the sausage mak…

I found it pretty strange to include in the readme as well. Like, imagine someone relied on fiverr or codementor.io to write this code. It'd be weird to say in the readme "I was fairly skeptical that I could get quality code written on Fiverr, but I tried it and it turns out it was pretty good!"

My guess is there were some push to doing anything related to AI at the company. I feel a lot of companies are doing this these days.

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

#58

Post by diggan »

kissgyorgy wrote: post #34
lichenwarp wrote: post #8

[flagged]

Just put a form on a website and you will see why... CloudFlare provides the solution, not causing the problem.

> Just put a form on a website and you will see why

We solved spam submissions on forms way before Cloudflare appeared, it isn't exactly a new problem...

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

#59

Post by spiderice »

paxys wrote: post #52
gokhan wrote: post #45

Earlier quoted context omitted.

> Not software engineers being kicked out ... but rather experienced engineers using AI to generate bits of code and then meticulously reviewing and testing them. 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. And the author is implementing a fairly technical project in this case. How about routine L…

Increased productivity means increased opportuntity. There isn't going to be a time (at least not anytime soon) when we can all sit back and say "yup, we have accomplished everything there is to do with software and don't need more engineers".

But there very well might be a time very soon where human's no longer offer economic value to the software engineering process. If you could (and currently you can't) pay an AI $10k/year to do what a human could do in a year, why would you pay the human 6 figures? Or even $20k?

Nobody is claiming that human's won't have jobs simply because "we have accomplished everything this is to do". It's that humans will offer zero economic value compared to AI because AI gets so good and so cheap.

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

#60

Post by thewebguyd »

unshavedyak wrote: post #5

Yup. I'm more skeptic than pro-AI these days, but nonetheless i'm still trying to use AI in my workflows. I don't actually enjoy it, i generally find it difficult to use as i have more trouble explaining what i want than actually just doing it. However it seems clear that this is not going away and to some degree it's "the future". I suspect it's better to learn the new tools of my craft than to be caught unaware. Wi…

> I don't actually enjoy it, i generally find it difficult to use as i have more trouble explaining what i want than actually just doing it.

This is my problem I run into quite frequently. I have more trouble trying to explain computing or architectural concepts in natural language to the AI than I do just coding the damn thing in the first place. There are many reasons we don't program in natural language, and this is one of them.

I've never found natural language tools easier to use, in any iteration of them, and so I get no joy out of prompting AI. Outside of the increasingly excellent autocomplete, I find it actually slows me down to try and prompt "correctly."

Post reply on HN