Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A look at Cloudflare's AI-coded OAuth library

neilmadden.blog

Post reply on HN
Print view View original

81–90 of 170 posts

Re: A look at Cloudflare's AI-coded OAuth library

#81

Post by skeeter2020 »

svara wrote: post #68
andersa wrote: post #66

Earlier quoted context omitted.

It's going to be like the pre-internet dark ages, but worse. Back then you only didn't find the information. Now, you find unlimited information, but it is all wrong.

I don't know, this sounds a lot like in the late 90s when we heard a lot about how anyone could put information on the internet and that you shouldn't trust what you read online. Well it turns out you can manage just fine. You shouldn't blindly trust anything. Not what you read, not what people say. Using LLMs effectively is a skill too, and that does involve deciding when and how to verify information.

>> Well it turns out you can manage just fine.

You missed the full context: you would never be able to trust a bunch of amateur randos self-policing their content. Turns out it's not perfect but better than a very small set of professionals; usually there's enough expertise out there, it's just widely distributed. The challenge this time is 1. the scale, 2. the rate of growth, 3. the decline in expertise.

>> Using LLMs effectively is a skill too, and that does involve deciding when and how to verify information.

How do you verify when ALL the sources are share the same AI-generated root, and ALL of the independent (i.e. human) experts have aged-out and no longer exist?

Re: A look at Cloudflare's AI-coded OAuth library

#82

Post by threeseed »

svara wrote: post #32
donatj wrote: post #24

Earlier quoted context omitted.

My question is kind of in this brave new world, where do the domain experts come from? Whose going to know this stuff?

LLMs make learning new material easier than ever. I use them a lot and I am learning new things at an insane pace in different domains. The maximalists and skeptics both are confusing the debate by setting up this straw man that people will be delegating to LLMs blindly. The idea that someone clueless about OAuth should develop an OAuth lib with LLM support without learning a lot about the topic is... Just wrong. Don…

Learning from LLMs is akin to learning from Joe Rogan.

You are getting a stylised view of a topic from an entity who lacks the deep understanding needed to be able to fully distill the information. But it is enough to gain enough knowledge for you to feel confident which is still valuable but also dangerous.

And I assure you that many, many people are delegating to LLMs blindly e.g. it's a huge problem in the UK legal system right now because of all the invented case law references.

Re: A look at Cloudflare's AI-coded OAuth library

#83

Post by skeeter2020 »

signatoremo wrote: post #73
belter wrote: post #58

Earlier quoted context omitted.

> But if you're willing to learn, this is rocket fuel. LLMs will tell you 1 or 2 lies for each 20 facts. Its a hard way to learn. They cant even get their urls right...

And you are saying human teachers or online materials won't lie to you once or twice for every 20 facts? no matter how small. Did you do any comparison?

it's not jsut the lies, but how it lies and the fact that LLMs are very hesitant to call out humans on their BS

Re: A look at Cloudflare's AI-coded OAuth library

#84

Post by skeeter2020 »

Earw0rm wrote: post #43
shswkna wrote: post #28

Earlier quoted context omitted.

Most important question on this entire topic. Fast forward 30 years and modern civilisation is entirely dependent on our AI’s. Will deep insight and innovation from a human perspective perhaps come to a stop?

No. Even with power tools, construction and joinery are physical work and require strength and skill. What is new is that you'll need the wisdom to figure out when the tool can do the whole job, and where you need to intervene and supervise it closely. So humans won't be doing any less thinking, rather they'll be putting their thinking to work in better ways.

to use your own example though, many of these core skills are declining, mechanized or viewed through a historical lens vs. application. I don't know if this is net good or bad, but it is very different. Maybe humans will think as you say, but it feels like there will be significantly less diverse areas of thought. If you look at the front page of HN as a snapshot of "where's tech these days" it is very homgenous compared to the past. Same goes for the general internet and the AI-content continues to grow. IMO published works are a precursor to future human discovery, forming the basis of knowledge, community and growth.

Re: A look at Cloudflare's AI-coded OAuth library

#85

Post by ipaddr »

diggan wrote: post #38
marcusb wrote: post #22

Earlier quoted context omitted.

I’m puzzled when I hear people say ‘oh, I only use LLMs for things I don’t understand well. If I’m an expert, I’d rather do it myself.’ In addition to the ability to review output effectively, I find the more closely I’m able to describe what I want in the way another expert in that domain would, the better the LLM output. Which isn’t really that surprising for a statistical text generation engine.

I guess it depends. In some cases, you don't have to understand the black box code it gives you, just that it works within your requirements. For example, I'm horrible at math, always been, so writing math-heavy code is difficult for me, I'll confess to not understanding math well enough. If I'm coding with an LLM and making it write math-heavy code, I write a bunch of unit tests to describe what I expect the functio…

Would you rather it be done incorrectly when others are expecting correctness or not at all? I would choose not at all.

Re: A look at Cloudflare's AI-coded OAuth library

#86

Post by skeeter2020 »

sarchertech wrote: post #51

I just finished writing a Kafka consumer to migrate data with heavy AI help. This was basically best case a scenario for AI. It’s throw away greenfield code in a language I know pretty well (go) but haven’t used daily in a decade. For complicated reasons the whole database is coming through on 1 topic, so I’m doing some fairly complicated parallelization to squeeze out enough performance. I’d say overall the AI was c…

> I’ve seen something closer to a 10-20% improvement.

The seems to match my experience in "important" work too; a real increase but not essentially changing the essence of software development. Brook's "No Silver Bullet" strikes again...

Re: A look at Cloudflare's AI-coded OAuth library

#87

Post by LgWoodenBadger »

sarchertech wrote: post #51

I just finished writing a Kafka consumer to migrate data with heavy AI help. This was basically best case a scenario for AI. It’s throw away greenfield code in a language I know pretty well (go) but haven’t used daily in a decade. For complicated reasons the whole database is coming through on 1 topic, so I’m doing some fairly complicated parallelization to squeeze out enough performance. I’d say overall the AI was c…

Complicated parallelization? That’s what partitions and consumers/consumer-groups are for!

Re: A look at Cloudflare's AI-coded OAuth library

#88

Post by slashdev »

threeseed wrote: post #82
svara wrote: post #32

Earlier quoted context omitted.

LLMs make learning new material easier than ever. I use them a lot and I am learning new things at an insane pace in different domains. The maximalists and skeptics both are confusing the debate by setting up this straw man that people will be delegating to LLMs blindly. The idea that someone clueless about OAuth should develop an OAuth lib with LLM support without learning a lot about the topic is... Just wrong. Don…

Learning from LLMs is akin to learning from Joe Rogan. You are getting a stylised view of a topic from an entity who lacks the deep understanding needed to be able to fully distill the information. But it is enough to gain enough knowledge for you to feel confident which is still valuable but also dangerous. And I assure you that many, many people are delegating to LLMs blindly e.g. it's a huge problem in the UK lega…

It depends very much on the quality of the questions. I get deep technical insight into questions I can't find anything on with Google.

Re: A look at Cloudflare's AI-coded OAuth library

#89

Post by OutOfHere »

This is why I have multiple LLMS review and critique my specifications document, iteratively and repeatedly so, before I have my preferred LLM code it for me. I address all important points of feedback in the specifications document. To do this iteratively and repeatedly until there are no interesting points is crucial. This really fixes 80% of the expertise issues.

Moreover, after developing the code, I have multiple LLMs critique the code, file by file, or even method by method.

When I say multiple, I mean a non-reasoning one, a reasoning large one, and a next-gen reasoning small one, preferably by multiple vendors.

Re: A look at Cloudflare's AI-coded OAuth library

#90

Post by diggan »

ipaddr wrote: post #85
diggan wrote: post #38

Earlier quoted context omitted.

I guess it depends. In some cases, you don't have to understand the black box code it gives you, just that it works within your requirements. For example, I'm horrible at math, always been, so writing math-heavy code is difficult for me, I'll confess to not understanding math well enough. If I'm coding with an LLM and making it write math-heavy code, I write a bunch of unit tests to describe what I expect the functio…

Would you rather it be done incorrectly when others are expecting correctness or not at all? I would choose not at all.

Well, given the context is math in video games, I guess I'd chose "not at all", if there was no way for me to verify it's correct or not. But since I can validate, I guess I'd chose to do it, although without fully understanding the internals.
Post reply on HN