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

111–120 of 552 posts

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

#111

Post by trollbridge »

realreality wrote: post #90
stego-tech wrote: post #82

Earlier quoted context omitted.

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.

You can hire a non-union plumber. There isn’t usually much of a price difference. Where I live, you can easily find a non-licenced plumber (called “moonlighting”, usually done by apprentices of licenced plumbers). A lot of people prefer not to since you’re on your own if something goes wrong.

Plumbing requires skill, particularly for difficult jobs, and also requires advanced equipment to do such a job in a reasonable amount of time, such as special cameras to inspect a septic tank or drain line without having to actually cut into it.

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

#112

Post by diggan »

eikenberry wrote: post #102
diggan wrote: post #40

Earlier quoted context omitted.

> They can get halfway there and then struggle immensely. Restart the conversation from scratch. As soon as you get something incorrect, begin from the beginning. It seems to me like any mistake in a messages chain/conversation instantly poisons the output afterwards, even if you try to "correct" it. So if something was wrong at one point, you need to go back to the initial message, and adjust it to clarify the promp…

I thought Claude still has a problem generating the same output for the same input? That you can't just rewind and rerun and get to the same point again.

> I thought Claude still has a problem generating the same output for the same input?

I haven't used Anthropic's models/software in a long time (months, basically forever in AI ecosystem), so don't know exactly how it works now.

But last time I used Claude, you could edit the first message, and then re-generate the assistants next message based on your edit. Most of the LLM interfaces has one or another way of doing this, I can't imagine they got rid of that feature.

What I'm suggesting isn't to use the exact same input (the first message), but rather change it so you remove the chances of something incorrect happening later after that.

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

#113

Post by jes5199 »

SkyPuncher wrote: post #89
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.

I guess what I mean is, I found the details sort of “mindless” before. Code that I could write in my sleep. Now I only have to do the thinky parts

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

#114

Post by noodletheworld »

kentonv wrote: post #95
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

I would say it ended up being much faster than had I written it by hand. It took a few days to produce this library -- it would almost certainly have taken me weeks to write it myself.

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?

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

#115

Post by layer8 »

SkyPuncher wrote: post #89
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.

This means that you fully trust the LLM to get the details right.

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

#116

Post by mikeocool »

thewebguyd wrote: post #75
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…

> 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…

Though arguably cloud infra made it so that a lot more companies who never would have built out a data center or leased a chunk of space in one were spinning up some serious infra in AWS or Azure -- and thus hiring at least 1-2 devops engineers.

Before the end of zero interest rate policy, all the sysadmins I knew who the made the transition to devops were never stuck looking for a job for long.

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

#117

Post by nicce »

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…

I am waiting for studies whether we have just an illusion of production or these actually save man hours in the long term in creation of production-level systems.

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

#118

Post by ookblah »

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 it off. You must be reviewing the entire time, but it takes a huge cognitive load off. You can rubber-duck debug with it.

I do agree if you have no idea what you are doing or are still learning it could be a detriment, but like anything it's just a tool. I feel for junior devs and the future. Lazy coders get lazier, those who utilize them to the fullest extent get even better, just like with any tech.

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

#119

Post by achierius »

thewebguyd wrote: post #75
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…

> 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…

To be clear, the number of people employed as "SREs" or "production engineers" is actually far, far higher (at least an order of magnitude) than in the days before cloud became a thing. There are simply far more apps / companies / businesses / etc. who use cloud hosting than there ever were doing on-prem work.

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

#120

Post by stego-tech »

dragonwriter wrote: post #108
stego-tech wrote: post #106

Earlier quoted context omitted.

> regulations require licensed plumbers to do the work Regulations come about because of repeated failures that end up harming the public. Regulations aren’t a dirty word, and aren’t obstacles to be “disrupted” in most cases. > plumbing unions have a financial interest in limiting the number of plumbers Golly gee, it’s almost as if - because we live in a society where everyone must work in order to survive - that ski…

> Regulations come about because of repeated failures that end up harming the public. Sometimes, but see also the concepts of “iron triangles” and “regulatory capture”.

You’re not wrong (examples include the US FCC, ZA’s Telekom, ye olde Standard Oil, vertical integrations…the list goes on, and even includes modern cloud services and AI tools, since the regulations they champion are often intended to block competitors with onerous compliance requirements), but in the context of the person I was replying to, they used “regulation” very much in the same context Uber/AirBnB and the SV Libertarian ilk decry “regulations”.

Regulations aren’t a binary (exclusively good or exclusively bad), yet so many of the HN cohort have drank the “exclusively bad and everyone can be trusted to make good decisions forever” koolaid that seeks to dismantle regulations wholesale.

Post reply on HN