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

441–450 of 552 posts

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

#441

Post by oblio »

fc417fc802 wrote: post #428
brailsafe wrote: post #390

Earlier quoted context omitted.

> I really don't agree with the idea that expert time would just be spent typing, and I'd be really surprised if that's the common sentiment around here. They didn't suggest that at all, they merely suggested that the component of the expert's work that would otherwise be spent typing can be saved, while the rest of their utility comes from intense scrutiny, problem solving, decision making about what to build and wh…

It's not just time spent typing. Figuring out what needs to be typed can be both draining and time consuming. It's often (but not always) much easier to review someone else's solution to the problem than it is to solve it from scratch on your own. Oddly enough security critical flows are likely to be one of the few exceptions because catching subtle reasoning errors that won't trip any unit tests when reviewing code…

The problem is, building something IS the destination. At least the first 5-10 times. Building and fixing along the way is what builds lasting knowledge for most people.

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

#442

Post by hn_throwaway_99 »

PeterStuer wrote: post #365
october8140 wrote: post #362

Earlier quoted context omitted.

It's a Jr Developer that you have to check all their code over. To some people that is useful. But you're still going to have to train Jr Developers so they can turn into Sr Developers.

I don't like the jr dev analogy. It neither has the same weaknesses nor the same strenghts. It's more like the genious coworker that has an overassertive ego and sometimes shows up drunk, but if you know how to work with them and see past their flaws, can be a real asset.

I also like your analogy, but it also explains why I find working with AI-assisted coding so mentally tiresome.

It's like with some auto-driving systems - I say it like having a slightly inebriated teenager at the wheel. I can't just relax and read a book, because then I'd die. But so I have to be more mentally alert than just driving myself because everything could be going smoothly and relaxed, but at any moment the driving system could decide to drive into a tree.

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

#443

Post by hn_throwaway_99 »

Cthulhu_ wrote: post #405
october8140 wrote: post #362

Earlier quoted context omitted.

It's a Jr Developer that you have to check all their code over. To some people that is useful. But you're still going to have to train Jr Developers so they can turn into Sr Developers.

I don't really agree; a junior developer, if they're curious enough, wouldn't just write insecure code, they would do self-study and find out best practices etc before writing code, including not storing plaintext passwords and the like.

You have clearly only ever worked with the creme de la creme of junior developers.

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

#444

Post by Izkata »

subarctic wrote: post #193
multimoon wrote: post #74

I think this reinforces that “vibecoding” is silly and won’t survive. It still needed immensely skilled programmers to work with it and check its output, and fix several bugs it refused to fix. Like anything else it will be a tool to speed up a task, but never do the task on its own without supervision or someone who can already do the task themselves, since at a minimum they have to already understand how the servic…

I get the sense that "vibecoding" is used like a strawman these days, something people keep moving the goal posts on so they can keep saying it's silly. Getting an LLM to write code for you that mostly works with some tweaks is vibe coding, isn't it?

No. Vibe coding is never even looking at the code and using the LLM as the only interface.

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

#445

Post by oblio »

thisissomething wrote: post #409
brailsafe wrote: post #392

Earlier quoted context omitted.

> No it doesn't. Typing speed is never the bottleneck for an expert How could that possibly be true!? Seems like it'd be the same as suggesting being constrained to analog writing utensils wouldn't bottleneck the process of publishing a book or research paper. At the very least such a statement implies that people with ADHD can't be experts.

Completely agree with you. I was working on the front-end of an application and I prompted Claude the following: "The endpoint /foo/bar is returning the json below ##json goes here##, show this as cards inside the component FooBaz following the existing design system". In less than 5 minutes Claude created code that: - encapsulated the api call - modeled the api response using Typescript - created a re-usable and res…

The thing is... does your code end there? Would you put that code in production without a deep analysis of what Claude did?

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

#446

Post by nijave »

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.

Isn't there some way to speed up with codegen besides using LLMs?

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

#447

Post by int_19h »

impure-aqua wrote: post #411
int_19h wrote: post #157

Earlier quoted context omitted.

Chatbot UIs really need better support for conversation branching all around. It's very handy to be able to just right-click on any random message in the conversation in LM Studio and say, "branch from here".

Certainly in my version of LM Studio (0.3.15) it has a branch button at the end of every message [0] [0] https://i.imgur.com/xZ2Fkn7.png

It does indeed. What I'm saying is that, for some mysterious reason, none of the first-party chatbot apps do that - ChatGPT, Claude, Gemini all lack this feature.

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

#448

Post by int_19h »

diggan wrote: post #159
int_19h wrote: post #157

Earlier quoted context omitted.

Chatbot UIs really need better support for conversation branching all around. It's very handy to be able to just right-click on any random message in the conversation in LM Studio and say, "branch from here".

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. But we already have different UX approaches for that - e.g. some IDEs watch for specially formatted comments to trigger code generation, so you literally just type what you want right there in the editor, exactly where you want the code to go.

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

#449

Post by TeMPOraL »

stego-tech wrote: post #147
TeMPOraL wrote: post #136

Earlier quoted context omitted.

> 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. I'd imagine AI is much cheaper on that front than grad students, whether you count marginal contribution, or total costs of building and utilization…

You really should read the papers and reporting coming out about the sheer cost of these AI models and their operation. It might seem significantly cheaper in the context of immediate impact, but those humans provide knock-on impacts that can decrease their environmental impact (especially if done in concert), while the current crop of AI is content burning NatGas turbines and guzzling up groundwater just so a human…

I'm not evaluating it in a vacuum.

> You really should read the papers and reporting coming out about the sheer cost of these AI models and their operation.

Unless I've missed something big, they're still showing what I said.

Obviously, AI has its cost. And it's going to be big, because the whole world is using it, and trying to develop better models.

> those humans provide knock-on impacts that can decrease their environmental impact (especially if done in concert)

Can you name three? As far as I know, humans are energy intensive and strongly carbon-negative in general - and there's only so much they can do to decrease it; otherwise we wouldn't be facing a climate crisis.

> the current crop of AI is content burning NatGas turbines

That's a misleading statement, not an argument. AI is powered by electricity, not natural gas. Electricity is fungible, and how it's generated is not relevant to to how it's used. Even if you can point at a data center that gets power directly and exclusively from a fossil fuel generator, the problem has nothing to do with AI, and the solution is not "less AI", but "power the data center from renewables or nuclear instead".

> I don’t see the value-add of these models deployed at scale, especially when their marketing continues focusing on synthetic benchmarks and lofty future-hype instead of immediately practicable applications (like this one was)

That's the crux of the issue. You don't see the value-add. I respectfully suggest to stop looking at benchmarks, to stop reading marketing materials and taking it seriously (always a good idea, regardless of the topic), to stop listening to linkedin "thought leaders". Instead, just look at it. Try using it, see how others are using it.

The value-add is real, substantial, and blindingly obvious. To me, it's one of the best uses of electricity today, in terms of value-add per kilowatt hour.

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

#450

Post by kentonv »

hn_throwaway_99 wrote: post #438
kentonv wrote: post #418

Earlier quoted context omitted.

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. :/

I just wanted to say thanks so much publishing this, and especially your comments here - I found them really helpful and insightful. I think it's interesting (though not unexpected) that many of the other commenters' comments here show what a Rorschach test this is. I think that's kind of unfortunate, because your experience clearly showed some of the benefits and limitations/pitfalls of coding like this in an object…

I find reviewing AI code less mentally tiring that reviewing human code.

This was a surprise to me! Until I tried it, I dreaded the idea.

I think it is because of the shorter feedback loop. I look at what the AI writes as it is writing it, and can ask for changes which it applies immediately. Reviewing human code typically has hours or days of round-trip time.

Also with the AI code I can just take over if it's not doing the right thing. Humans don't like it when I start pushing commits directly to their PR.

There's also the fact that the AI I'm prompting is, obviously, working on my priorities, whereas humans are often working on other priorities, but I can't just decline to review someone's code because it's not what I'm personally interested in at that moment.

When things go well, reviewing the AI's work is less draining than writing it myself, because it's basically doing the busy work while I'm still in control of high-level direction and architecture. I like that. But things don't always go well. Sometimes the AI goes in totally the wrong direction, and I have to prompt it too many times to do what I want, in which case it's not saving me time. But again, I can always just cancel the session and start doing it myself... humans don't like it when I tell them to drop a PR and let me do it.

Personally, I don't generally get excited about mentoring and collaborating. I wish I did, and I recognize it's an important part of my job which I have to do either way, but I just don't. I get excited primarily about ideas and architecture and not so much about people.

Post reply on HN