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

451–460 of 552 posts

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

#451

Post by fragmede »

signa11 wrote: post #399
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…

> ... Still saves a lot of time vs typing everything from scratch ... how ? the prompts have still to be typed right ? and then the output examined in earnest.

not if you don't want to. speech to text is pretty good these days, and even eg aider has a /voice command thanks to OpenAI's whisper.

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

#453

Post by cpursley »

lsllc wrote: post #277
Workaccount2 wrote: post #212

Earlier quoted context omitted.

>My brother for example built a thing with Microsoft copilot that helped automate more in his manufacturing facility (used to be paper). I have harped on this endlessly as a non-programmer working a non-tech job, with 7 "vibe-coded" programs now being used daily by people at my company. I am sorry, but the tech world is completely missing the forest for the trees here. LLM's are talked about purely as tools that were…

> >My brother for example built a thing with Microsoft copilot that helped automate more in his manufacturing facility (used to be paper). > I have harped on this endlessly as a non-programmer working a non-tech job, with 7 "vibe-coded" programs now being used daily by people at my company. Aren't AI coding agent(s) just the next iteration of democratizing app development? This has happened before with Microsoft Acce…

From what I understand, what he built was a copilot assisted Access app. He would have not had the time nor skillset without the copilot thing. And they don't have the budget for a bespoke app.

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

#454

Post by shaky-carrousel »

fastball wrote: post #404
signa11 wrote: post #399

Earlier quoted context omitted.

> ... Still saves a lot of time vs typing everything from scratch ... how ? the prompts have still to be typed right ? and then the output examined in earnest.

A prompt can be as little as a sentence to write hundreds of lines of code.

Hundreds of lines that you have to carefully read and understand.

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

#457

Post by skydhash »

dns_snek wrote: post #413
thisissomething wrote: post #410

Earlier quoted context omitted.

Yeah, but how fast can you write compared to how fast you think? How many times have you read a story card and by the time you finished reading it you thought "It's an easy task, should take me 1 hour of work to write the code and tests"? In my experience, in most of those cases the AI can do the same amount of code writing in under 10 minutes, leaving me the other 50 minutes to review the code, make/ask for any nece…

I don't know anyone who can think faster than they can type (on average), they would have to have an IQ over 150 or something. For mere mortals like myself, reasoning through edge cases and failure conditions and error handling and state invariants takes time. Time that I spend looking at a blinking cursor while the gears spin, or reading code. I've never finished a day where I thought to myself "gosh darn, if only I…

You could be fast if you were coding only the happy path, like a lot of juniors do. Instead of thinking about trivial things like malformed input, library semantics, framework gotchas and what not.

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

#458

Post by dismalaf »

victorbjorklund wrote: post #376
rienbdj wrote: post #351

The commits are revealing. Look at this one: > Ask Claude to remove the "backup" encryption key. Clearly it is still important to security-review Claude's code! > prompt: I noticed you are storing a "backup" of the encryption key as `encryptionKeyJwk`. Doesn't this backup defeat the end-to-end encryption, because the key is available in the grant record without needing any token to unwrap it? I don’t think a non-expe…

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…

> Still saves a lot of time vs typing everything from scratch

Probably very language specific. I use a lot of Ruby, typing things takes no time it's so terse. Instead I get to spend 95% of my time pondering my problems (or prompting the LLM)...

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

#459

Post by lovich »

azemetre wrote: post #407
Culonavirus wrote: post #403

Earlier quoted context omitted.

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 this because the LLMs had like a million+ react tutorials/articles/books/repos to train on? I mean I try to use them for svelte or vue and it still recommends react snippets sometimes.

I use https://visualstudio.microsoft.com/services/intellicode/ for my IDE which learns on your codebase, so it does end up saving me a ton of time after its learned my patterns and starts suggesting entire classes hooked up to the correct properties in my EF models.

It lets me still have my own style preferences with the benefit of AI code generation. Bridged the barrier I had with code coming from Claude/ChatGPT/etc where its style preferences were based on the wider internets standards. This is probably a preference on the level of tabs vs spaces, but ¯\_(ツ)_/¯

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

#460

Post by victorbjorklund »

dismalaf wrote: post #458
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…

> Still saves a lot of time vs typing everything from scratch Probably very language specific. I use a lot of Ruby, typing things takes no time it's so terse. Instead I get to spend 95% of my time pondering my problems (or prompting the LLM)...

It can create a whole dashboard view in elixir in a few seconds that is 100 lines long. No way I can type that in the same time.
Post reply on HN