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

491–500 of 552 posts

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

#491

Post by aerhardt »

lapcat wrote: post #431
chii wrote: post #430

Earlier quoted context omitted.

> They want to turn artists and craftsmen into assembly line supervisors. the same was uttered by blacksmiths and other craftsman who has been displaced by technology. Yet they are mercilessly crushed. Your enjoyment of a job is not a consideration to those paying you to do it; and if there's a more efficient way, it will be adopted. The idea that your job is your identity may be at fault here - and when someone's id…

> the same was uttered by blacksmiths and other craftsman who has been displaced by technology. Yet they are mercilessly crushed. This is misleading. The job of blacksmith wasn't automated away. There's just no demand for their services anymore, because we no longer have knights wearing armor, brandishing swords, and riding horses. In contrast, computer software is not disappearing; if anything, it's becoming ubiquit…

> This is misleading. The job of blacksmith wasn't automated away. There's just no demand for their services anymore, because we no longer have knights wearing armor, brandishing swords, and riding horses. In contrast, computer software is not disappearing; if anything, it's becoming ubiquitous.

Why didn't blacksmiths produce rail tracks, if not because they were replaced by more efficient processes? One could say iron and steel became as ubiquitous during the Industrial Revolution as computer software is becoming today...

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

#492

Post by aerhardt »

mattgreenrocks wrote: post #435
lapcat wrote: post #414

If my future career consists of constantly prompting and code-reviewing a semi-competent, nonhuman coder in order to eventually produce something decent, then I want no part in that future, even if it's more "efficient" in the sense of taking less time overall. That sounds extremely frustrating, personally unrewarding, alienating. I've read the prompts and the commit messages, and to be honest, I don't have the patie…

I deeply resent the notion that we engineers should let non-engineers tell us how to achieve agreed-upon objectives (e.g. "use LLMs more!"). I'm happy to use LLMs when they are useful. If I have to babysit them excessively, then it's a double loss: I'm not accruing domain knowledge, and I'm wasting time. The contract of work I was sold in the early 2000s: decision makers specify what should be be built, and what the…

> I deeply resent the notion that we engineers should let non-engineers tell us how to achieve agreed-upon objectives

This is not how it works. The technology will prevail or not based on whether people using it are noticeably more efficient using it, not the whims of your CEO - nor yours!

You then make an argument as to why you think the net gain will not be positive, which is fine, but that crucial question is what everything hinges on.

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

#494

Post by aerhardt »

kentonv wrote: post #33
hattmall wrote: post #7

I guess for me the questions is, at what point do you feel it would be reasonable to this without the experts involved in your case? As an edit, after reading some of the prompts, what is the likelihood that a non-expert could even come up with those prompts? The really really interesting thing would be if an AI could actually generate the prompts.

(I'm the author of this library -- or, the guy who prompted the AI at least.) I absolutely would not vibe code an OAuth implementation! Or any other production code at Cloudflare. We've been using more AI internally, but made this rule very clear: the human engineer directing the AI must fully understand and take responsibility for any code which the AI has written. I do think vibe coding can be really useful in low-…

> I do think vibe coding can be really useful in low-stakes environments, though. I vibe-coded an Android app to use as a baby monitor (it just streams audio from a Unifi camera in the kid's room). I had no previous Android experience, and it would have taken me weeks to learn without AI, but it only took a few hours with AI.

Bro, you're still an engineer at Cloudflare!

One problem I see with "vibe coding" is how it means one thing if Ilya Sutskever says it, and another if a non-tech executive parrots it and imagines "citizens developers" coding their own business apps.

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

#495

Post by ksenzee »

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.

This can’t be stressed enough: it depends on what you’re doing. Developers talking about whether LLMs are useful are just talking past each other unless they say “useful for React” or “useful for Rust.” I mostly write Drupal code, and the JetBrains LLM autocomplete saves me a few keystrokes, maybe. It’s not amazing. My theory is that there just isn’t much boilerplate Drupal code out there to train on: everything possible gets pushed out of code and into configuration + UI. If I were writing React components I’d be having an entirely different experience.

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

#496

Post by aerhardt »

qsort wrote: post #9
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…

Probably unrelated to the broader discussion, but I don't think the "skeptic vs pro-AI" distinction even makes that much sense. For example, I usually come off as being relatively skeptic within the HN crowd, but I'm actually pushing for more usage at work. This kind of "opinion arbitrage" is common with new technologies.

Someone has mentioned in another thread that there is an increasing divide between "discourse skeptics" and fundamental skeptics, more like luddites.

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

#497

Post by lapcat »

aerhardt wrote: post #491
lapcat wrote: post #431

Earlier quoted context omitted.

> the same was uttered by blacksmiths and other craftsman who has been displaced by technology. Yet they are mercilessly crushed. This is misleading. The job of blacksmith wasn't automated away. There's just no demand for their services anymore, because we no longer have knights wearing armor, brandishing swords, and riding horses. In contrast, computer software is not disappearing; if anything, it's becoming ubiquit…

> This is misleading. The job of blacksmith wasn't automated away. There's just no demand for their services anymore, because we no longer have knights wearing armor, brandishing swords, and riding horses. In contrast, computer software is not disappearing; if anything, it's becoming ubiquitous. Why didn't blacksmiths produce rail tracks, if not because they were replaced by more efficient processes? One could say ir…

> Why didn't blacksmiths produce rail tracks

This is really a silly and pointless discussion, as well as totally irrelevant.

The linked article made very clear that Claude had to be closely, strictly guided and supervised by expert software developers. Claude is not threatening them with extinction.

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

#498

Post by Flemlo »

immibis wrote: post #472
Flemlo wrote: post #388

Earlier quoted context omitted.

Are you good in math definitions or is this an opinion? For me a compressed model learning rules through statistics is not statistics anymore. Physic rules are not statistics.

Of course they are. Force has a strong correlation with mass times acceleration. Objects at rest have a high chance of being observed to remain at rest. And so on.

Statistic is not the same as constant equations.

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

#499

Post by dang »

aerhardt wrote: post #485
JackSlateur wrote: post #483

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.

Can you please make your substantive points without name-calling like "This is hogwash"? Your comment would be just fine without that bit.

This is in the site guidelines: https://news.ycombinator.com/newsguidelines.html.

"When disagreeing, please reply to the argument instead of calling names. 'That is idiotic; 1 + 1 is 2, not 3' can be shortened to '1 + 1 is 2, not 3."

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

#500

Post by kentonv »

827a wrote: post #419
victorbjorklund wrote: post #376

Earlier quoted context omitted.

That is how LLM:s should be used today. An expert prompts it and checks the code. Still saves a lot of time vs typing everything from scratch. Just the other day I was working on a prototype and let claude write code for a auth flow. Everything was good until the last step where it was just sending the user id as a string with the valid token. So if you got a valid token you could just pass in any user id and become…

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…

> This workers-oauth-provider project is 1200 lines of code. An expert should be able to write that on the scale of an hour.

Are you being serious here?

Let's do the math.

1200 lines in a hour would be one line every three seconds, with no breaks.

And your figure of 1200 lines is apparently omitting whitespace and comments. The actual code is 2626 lines. Let's say we ignore blank lines, then it's 2251 lines. So one line per ~1.6 seconds.

The best typists type like 2 words per second, so unless the average line of code has 3 words on it, a human literally couldn't type that fast -- even if they knew exactly what to type.

Of course, people writing code don't just type non-stop. We spend most of our time thinking. Also time testing and debugging. (The test is 2195 lines BTW, not included in above figures.) Literal typing of code is a tiny fraction of a developer's time.

I'd say your estimate is wrong by at least one, but realistically more likely two orders of magnitude.

Post reply on HN