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

81–90 of 552 posts

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

#81

Post by uludag »

bigstrat2003 wrote: post #41
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…

> but rather experienced engineers using AI to generate bits of code and then meticulously testing and reviewing them. My problem is that (in my experience anyways) this is slower than me just writing the code myself. That's why AI is not a useful tool right now. They only get it right sometimes so it winds up being easier to just do it yourself in the first place. As the saying goes: bad help is worse than no help a…

I feel this is on point. So not only is there the time lost correcting and testing AI generated code, but there's also the mental model you build of the code when you write it yourself.

Assuming you want a strong mental model of what the code does and how it works (which you'd use in conversations with stakeholders and architecture discussions for example), writing the code manually, with perhaps minor completion-like AI assistance, may be the optimal approach.

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

#82

Post by stego-tech »

waynenilsen wrote: post #73
stego-tech wrote: post #53

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…

most engineering is glorified plumbing so as far as labour productivity goes, this should go a long way

I doubt it, for the simple reason that literal plumbers still make excellent money because plumbing is ultimately bespoke output built on standards.

Everyone wants to automate the (proverbial) plumbing, until shit spews everywhere and there’s nobody to blame but yourself.

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

#83

Post by hombre_fatal »

diggan wrote: post #72
hombre_fatal wrote: post #62

Earlier quoted context omitted.

It's still just barking up the wrong tree. You're seeing a downstream effect of widespread abuse on the internet and complaining about people trying to mitigate it.

> It's like complaining that you have to ask someone at Walmart to take a product out of the lockbox so that you can buy it. Kind of similar I guess, but mostly not. Never been to Walmart, so not sure what I'd expect, but I'm guessing that if I ask them to give me that item, they'll give it to me? Because that's not how Cloudflare's captchas work. Sometimes they'll keep on coming indefinitely, until you give up and t…

Dang, you're fast. I almost immediately deleted the Walmart part because the analogy misses the detail that website operators are the ones choosing to use Cloudflare to protect their services.

And it's something you've missed to. Because yeah, captchas are annoying, but it's the result of web service operators trying to avoid the ever increasing amount of abusive traffic, and there's definitely collateral damage as abusive traffic looks more and more human (e.g. residential IP botnets being dirt cheap).

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

#84

Post by stego-tech »

TeMPOraL wrote: post #66
stego-tech wrote: post #53

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…

> 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. Personally I hope this will materialize, at the very least because there's…

I don’t consider that “new” research, personally - because AI boosters don’t consider that “new”. The future they hype is one where these LLMs can magic up entirely new fields of research and study without human input, which isn’t how these models are trained in the first place.

That said, yes, it could be highly beneficial for identifying patterns in existing research that allows for new discoveries - provided we don’t trust it blindly and actually validate it with science. Though I question its value to society in burning up fossil fuels, polluting the atmosphere, and draining freshwater supplies compared to doing the same work with Grad Students and Scientists with the associated societal feedback involved in said employment activities.

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

#85

Post by chrisweekly »

belter wrote: post #43
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…

The million-dollar question is not whether you can review at the speed the model is coding. It is whether you can trust review alone to catch everything. If a robot assembles cars at lightning speed... but occasionally misaligns a bolt, and your only safeguard is a visual inspection afterward, some defects will roll off the assembly line. Human coders prevent many bugs by thinking during assembly.

THIS.

IMHO more rigorous test automation (including fuzzing and related techniques) is needed. Actually that holds whether AI is involved or not, but probably more so if it is.

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

#86

Post by JimDabell »

bigstrat2003 wrote: post #41
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…

> but rather experienced engineers using AI to generate bits of code and then meticulously testing and reviewing them. My problem is that (in my experience anyways) this is slower than me just writing the code myself. That's why AI is not a useful tool right now. They only get it right sometimes so it winds up being easier to just do it yourself in the first place. As the saying goes: bad help is worse than no help a…

> My problem is that (in my experience anyways) this is slower than me just writing the code myself.

How much experience do you have writing code vs how much experience do you have prompting using AI though? You have to factor in that these tools are new and everybody is still figuring out how to use them effectively.

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

#87

Post by SkyPuncher »

nisegami wrote: post #32
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…

Same. But I personally find it a lot easier to do those bits at the end than to begin from a blank file/function, so it's a good match for me.

Same here. Sometimes you just need time to stew in the problem/solution space.

LLMs let me be ultraproductive upfront then come in at the end to clean up when I have a full understanding.

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

#88

Post by DJBunnies »

I feel like well defined RFCs and standards are easily coded against, and I question the investment/value/time tradeoff here. These things happily regurgitate training data, but seriously struggle when they don’t have a pool of perfect examples to pull from.

When Claude can do something new, then I think it will be impressive.

Otherwise it’s just piecing together existing examples.

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

#89

Post by SkyPuncher »

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

> 2. It’s way more cognitively demanding than writing code the old-fashioned way

Funnily, enough, I find the exact opposite. I feel so much relief that I don't have to waste time figuring out every, single detail. It frees me up to focus on architectural and higher level changes.

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

#90

Post by realreality »

stego-tech wrote: post #82
waynenilsen wrote: post #73

Earlier quoted context omitted.

most engineering is glorified plumbing so as far as labour productivity goes, this should go a long way

I doubt it, for the simple reason that literal plumbers still make excellent money because plumbing is ultimately bespoke output built on standards. Everyone wants to automate the (proverbial) plumbing, until shit spews everywhere and there’s nobody to blame but yourself.

Plumbers make excellent money because regulations require licensed plumbers to do the work, and plumbing unions have a financial interest in limiting the number of plumbers.

But anybody can do plumbing. It’s not rocket science.

Post reply on HN