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

181–190 of 552 posts

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

#181

Post by Flemlo »

weinzierl wrote: post #175

"I thoughts LLMs were glorified Markov chain generators" "the code actually looked pretty good. Not perfect, but I just told the AI to fix things, and it did. I was shocked." These two views are by no means mutually exclusive. I find LLMs extremely useful and still believe they are glorified Markov generators. The take away should be that that is all you need and humans likely are nothing more than that.

The way the input doesn't match the output should imply that it's not just statistics.

As soon as compression happens, optimization happens which can lead to rules/learning of principles which got feed by statistics.

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

#182

Post by seunosewa »

sceptic123 wrote: post #63
diggan wrote: post #51

Earlier quoted context omitted.

> these tools don't have actual understanding, and are instead producing emergent output from pooling an incomprehensibly large set of pattern-recognized data I mean, bypassing the fact that "actual understanding" doesn't have any consensus about what it is, does it matter if it's "actual understanding" or "kind of understanding", or even "barely understanding", as long as it produces the results you expect?

> as long as it produces the results you expect? But it's more the case of "until it doesn't produce the results you expect" and then what do you do?

Then you teach it. Even humans don't always produce the results we expect.

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

#184

Post by varispeed »

The thing is you need to know what exactly LLM should create and you need to know what it is doing wrong and tell it to fix it. Meaning, if you don't already have skill to build something yourself, AI might not be as useful. Think of it as keyboard on steroids. Instead of typing literally what you want to see, you just describe it in detail and LLM decompresses that thought.

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

#185

Post by baq »

steveklabnik wrote: post #174
qsort wrote: post #9

Earlier quoted context omitted.

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.

One recent post I read about improving the discourse (which I seem to have lost the link...) agrees, but in a different way: adding a "capable vs not" axis. that is, "I believe AI is good enough to replace humans, and I am pro" is different than "I believe AI is good enough to replace humans, and I am against" and while "I believe AI is not good enough to replace humans, and I am pro" is a weird position to take, "I…

> "I believe AI is not good enough to replace humans, and I am pro" is a weird position to take

Huh? The recipe how to be in this position is literally in the readme of the linked project. You don’t even have to believe it, you just have to work it.

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

#186

Post by Bjartr »

dkdcio wrote: post #138
sceptic123 wrote: post #70

If you need to be an expert to use AI tools safely, what does that say about AI tools?

Genuinely curious what your point is? Do you know how to use a ventillator? A A timing gun? A tonometer? A keratometer? Can you use all of those in a "production" setting safely without expertise?

They didn't make a point, they asked a question. Sometimes people do still ask questions because they're interested in the answer.

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

#187

Post by kentonv »

weinzierl wrote: post #175

"I thoughts LLMs were glorified Markov chain generators" "the code actually looked pretty good. Not perfect, but I just told the AI to fix things, and it did. I was shocked." These two views are by no means mutually exclusive. I find LLMs extremely useful and still believe they are glorified Markov generators. The take away should be that that is all you need and humans likely are nothing more than that.

I suppose it's all a continuum and we can each have different opinions on what the threshold for "glorified markov generator" is.

But there have been many cases in my experience where the LLM could not possibly have been simply pattern-matching to something it had seen before. It really did "understand" the meaning of the code by any definition that makes sense to me.

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

#188

Post by jsnell »

Denzel wrote: post #173
jsnell wrote: post #160

Earlier quoted context omitted.

Inference is actually quite cheap. Like, a highly competitive LLM can cost 1/25th of a search query. And it is not due to inference being subsidized by VC money. It's also getting cheaper all the time. Something like 1000x cheaper in the last two years at the same quality level, and there's not yet any sign of a plateau. So it'd be quite surprising if the only long-term business model turned out to be subscriptions.

Can you link to any sources that support your claim?

Sure. Here's something I'd written on the subject that I'd left lying in my drafts folder for a month, but I've now published just for you :)

https://www.snellman.net/blog/archive/2025-06-02-llms-are-ch...

It has links to public sources on the pricing of both LLMs and search, and explains why the low inference prices can't be due the inference being subsidized. (And while there are other possible explanations, it includes a calculator for what the compound impact of all of those possible explanations could be.)

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

#189

Post by prmph »

stego-tech wrote: post #110
btown wrote: post #97

Earlier quoted context omitted.

It's said that much of research is data janitorial work, and from my experience that's not just limited to the machine learning space. Every research scientist wishes that they had an army of engineers to build bespoke tooling for their niche, so they could get back to trying ideas at the speed of thought rather than needing to spend a day writing utility functions for those tools and poring over tables to spot anoma…

> Vibe-coding won't be a net creativity gain to a researcher affected by vibe-immigration-policy, vibe-grant-availability, and vibe-firings, for all of which the unpredictability is a punitive design goal. Quite literally this is what I’m trying to get at with my resistance to LLM adoption in the current environment. We’re not using it to do hard work, we’re throwing it everywhere in an intentional decision to dumb d…

This is one of the best comments about the current AI hype.

The elite really don't see why the proletariat should be interested in, or enjoy the dignity of, actual skill and quality.

Hence the enshitification of everything, and now AI promises to commoditize everything into slop.

Sad because it is the very deoth of society that has birthe

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

#190

Post by hn_acc1 »

kentonv wrote: post #132
thewebguyd wrote: post #75

Earlier quoted context omitted.

> 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…

I think there's a huge huge space of software to build that isn't being touched today because it's not cost-effective to have an engineer build them. But if the time it takes an engineer to build any one thing goes down, now there are a lot more things that are cost effective. Consider niche use cases. Every company tends to have custom processes and workflows. Think about being an accountant at one company vs. anoth…

After 30+ years in the software field, and a user for 40+, having at times heavily customized my desktop or editor, for example - I've concluded that the best thing for most apps is for me to learn to use them with stock settings.

Why? Inevitably, I changed positions / jobs / platforms, and all that effort was lost / inapplicable, and I had to relearn to use the stock settings anyway.

Now, I understand that some companies have different setups, but it might just make more sense to change the company's accounting procedures (if possible) to conform to most accounting software defaults, rather than invest heavily in modifying the setup, unless you're a huge conglomerate and can keep people on staff. Why? Because someone, somewhere will have to maintain those changes. Sure, you can then hire someone else to update those changes - but guess what? Most likely, unless they open-source their changes, no LLM will have seen those changes, and even if they are allowed to fine-tune on it, they'll have seen exactly ONE instance of these changes. Odds they'll get everything right, AND the person using the LLM will recognize when it doesn't go right? Oh right, they invested in hundreds of unit tests to ensure everything works as expected even with changes, and I'm the tooth fairy..

Post reply on HN