HN Simulatornew | past | comments | lists | submit | oliwarner's commentslogin

Weird that they lay all this at the feet of vibecoding. I've asked for authentication systems several times and they've tended to come with pretty good feature-sets. Perhaps it's because I know what I'm asking for.

Edit: I've just tried to log in and it's failed through both Google and email. Whatever they've done, they haven't tested it well.


Yes, but you're not vibe coding when you ask for an authentication system. You know what you mean by an authentication system and can tell when what the AI delivers is insufficient. A vibe coder can't.

The problem with vibe coding isn't the AI, it's how people use it. It's that people with no idea of what they're doing, now think they can do what used to require an expert.


the part that is weird to me: nobody really knows how much they know about designing a system in plain english until they try it. i would not have thought i knew enough words to be dangerous (self-complimentary), but i clearly do. i still think of myself as a know-nothing vibe coder, and the only way to prove it one way or the other would basically be to go back to college. lol

You do not code your authentication system, in 99% of cases. Take an external provider or a selfhosted OSS project.

We're talking vibing here, not coding. And who knows what the agent will decide from fuzzy prompts, take an external provider or create a new one from scratch?

That's fair, I do, but it's alien to me that they wouldn't at least start with the old system as a starting point or another system, or that the LLM wouldn't make that link.

To get what tfa is describing, you'd need to explicitly request a dumbed down system, use a really shitty LLM, or both.

Honestly I'd sooner believe this is the result of a highschooler than a LLM.


Oh, absolutely. Why even try to fix what wasn't broken, and 'fix' it in a way that's likely to break it? It betrays a deep misunderstanding of what the site does and is supposed to do.

I've got no problem with people vibe coding a personal project or a prototype or something, but when you've got code in production, that a business depends on, you've got to be a massive idiot to blindly start rewriting it in this way.


I think they wanted a site refresh, and instead of doing it visually and/or adding features at the same time (people do this still, I think its okay), they likely thought that due to AI assistance it would be easy to actually start from scratch.

Not sure why you couldn't take the "its easy with AI" path and actually refresh the current codebase.

This is hearsay mind you, I don't know how much of their old site is there...


It is the fault of vibe coding, the sell has consistently been AI solves all of this. Clearly someone somewhere has to know what the system should or shouldn't do.

No? I have heard literally nobody say that AI guarantees insecure code will never be written again.

Erm.

I've seen a number of companies (and HN contributors) explain that AI produces code that is better than coders. Which, of course, if you actually think about it carefully, doesn't guarantee anything about security, but that's not how executives understand the sentence.


> I've seen a number of companies (and HN contributors) explain that AI produces code that is better than coders

Feels like a straw man argument.

When I've seen comments like this it's always been related to giving them narrowly focused work.

E.g.

- fix specific security issue in existing auth system.

- find cause of and fix a specific bug

Etc.

If anyone is claiming they get better results from less specific prompts like "build me a login system" I haven't seen it. I'm sure there are people making those claims - it's the internet, you can find a thousand people backing any dumb viewpoint on Twitter - but it's definitely not a widely accepted viewpoint amongst professionals.


> When I've seen comments like this it's always been related to giving them narrowly focused work.

FWIW, I don't think that I've ever seen this claim being scoped in any manner.


They do it by implication:

AI Companies: "AI is now amazing at spotting insecure code"

Implication: If it can spot it, all the code it writes must therefore be secure


> Implication: If it can spot it, all the code it writes must therefore be secure

Which is funny to anyone that's prompted one to review some code for security problems where that code is something it generated previously.


I've had a co-worker "review" my change using an LLM, and the comment concerned a pre-existing behavior... Which was introduced by the same person.

But you have asked for something specific. An authentication system.

If you ask it to rebuild a site that has x, y and z features, the AI will output an average outcome because it's doing broader implementations. Context and thinking only goes so far unless you have thousands upon thousands to burn in tokens.


The scope of the Humble site feels like 2 free months of Copilot. I've done more with less.

My read was that they didn't test it. How do can someone compare the old version vs the new one and miss something like 2FA?

This isn’t a matter of testing — this is the output of an executive that learned everything they know about AI from the all-in podcast and Kevin Roos, deciding to not to have a trusted, qualified technologist before hiring someone/some shop that doesn’t know what they’re doing, which delegated not only coding, but also technical design, architecture, implemention, auditing, etc. to a chatbot. Anybody that knows that tests are necessary doesn’t need a test to check the most basic, broad-stroke sanity of an authentication system. I’ll bet whoever made the sale was really great at getting people, probably themselves included, really excited about AI coding agents without understanding the important caveats.

This was likely the result of a CEO replacing their entire dev team by:

Build and maintain our website. Add features as needed. Rewrite everything as needed. Deploy automatically. Make it compatible. Make it fast, secure and bug free. Make it cyber. Make it cloud. Don't make mistakes.


"Make it cyber. Make it cloud. Don't make mistakes" This is going to be my new motto from now on

But yeah, you description sounds pretty accurate from the outcome


I suspect LLMs are going to be used as convenient scapegoats for the foreseeable future. "Boss, I didn't fuck up, Claude did."

"A computer can never be held accountable, therefore a computer must never make a management decision." - IBM slide deck, 1979

Scratch the "management" and replace it with "critical" and we probably have a near universal statement (maybe also add that no sole person should make such decisions).


Might be worse.

1. Boss orders dev to use Claude for everything. Claims proudly "we're AI-native", "we're using an AI factory". Disincentivizes any kind of human review.

2. Dev eventually gives in.

3. Claude makes mistakes.

4. Dev gets blamed, because they're the "human [fuse] in the loop".


"And who used Claude on it? You did? Well..."

AI loves copying existing patterns in legacy code without asking, even if they're super-dumb. It's like it reads bad code and that anchors the pattern in its thinking.

It might have been some internal testing mechanism that's been corrupted. Or if they had an existing hole the AI probably convinced itself that was what was necessary.

That's one of the disadvantages of them hiding the "thinking" output they used to cycle through, sometimes you could spot that happening.


> It might have been some internal testing mechanism that's been corrupted.

Yeah, I've seen so often the agent just getting rid of tests (either by removing them or by corrupting them) that it stopped being funny a long time ago.


Yeah, not a bad shout.

That's still dumber than I've come to expect from LLMs but as others have pointed out, I'm a developer who uses LLMs as a tool, not a manager using a LLM as a developer.


The most important part would be that none of that work (input, work process or work product) ever left the building.

If you leak your client's confidence, you'd be liable for serious damages.


I know "think of the children" is a cliché for censorship, but as the adults, we do have to think about the children.

We built these toys and networks and commoditised the hardware and access so it's just pocket money and then built services where kids can just vanish into without oversight.

> If these were really concerns...

Given several countries are passing online safety laws around the very things you highlight, yes. I think they really are all concerns.


Gosh I sure am glad natural gas isn't a major fuel for grid-based generation, and under contention with residential heating. If that were the case, all that extra demand on a limited resource could drive prices up.

Now you could argue that billionaires, their investors and loan sharks should be allowed to buy up gas —perfectly legal— but it's actively screwing up people's lives.


What should the stock market be?

I understand that at a lofty, ethical plane, it's a reflection of value, of growth and progress and confidence in all of that.

But in practice, it's not even gambling. It's humanity's hope bastardised by HFT and recurring insider trading. It's confidence for all the wrong reasons, institutional HODL.

It's a mugs' game.


The stock market should be a mechanism for allocation of wealth that helps the country and the economy. What people have done over the last 50 years is called "a race to the bottom", where everyone puts personal wealth gain over social behavior and teamwork like what made america great in the first place. The moral collapse of the US lead the way to the collapse of it's power.


> It's a mugs' game.

Over the long term it’s the investment class most likely to grow capital.

Occasionally there are long periods where returns are low (or even negative), but in terms of risk it’s the least risky place to put your money compared to all the alternatives (if properly diversified).

(Not financial advice, just my rule-of-thumb understanding)


> Occasionally there are long periods where returns are low (or even negative), but in terms of risk it’s the least risky place to put your money compared to all the alternatives (if properly diversified).

This is a very US-centric viewpoint, my recollection is that the FTSE didn't beat inflation for like a 20 year period.

That being said, index funds focused on equity are definitely a good way of getting reasonable returns over time (as long as you don't retire into a massive crash).


But the idea in early e-commerce was sane. Undercut retail on cost, increase profit. The ones that failed, failed on execution. Pets.com failed because you can't ship massive bags of food below cost and expect to make a profit.

Setting fire to cash to have the best model that anyone else can also do isn't a business model. They're never going to be able to stop setting fire to cash or they'll fall behind immediately. Their user base will not pay the bills. It's an obviously bad investment.


I'm not sure it's irrational. It's perhaps oversensitive. There are dozens of nuclear power incidents rated at levels of 5+, affecting the wider region.

In the UK, Sellafield was a nightmare. Lots of less serious slip ups and malfunctions punctuated by a few critical incidents, between 1954 and 2003. You might understand why yesterday's Green Party might think it an issue worth pursuing.


If you're willing to pay cash?

This sounds more like tax evasion than paperwork avoidance.


"Paying cash" doesn't mean literally that in this context. Cash, credit card, check... "Paying cash" just means paying directly without involving insurance.


Could be that. Could be they don't want to pay 3% to a middle.


It also means not paying credit card fees, not having to chase down bounced checks, etc. Cash means the money is there, which has value.


When I "pay cash" for a medical procedure it's actually with a credit card.

Just means I'm paying them directly instead of making them deal with my insurance.


I mean pay 100% of the cost yourself rather than relying on insurance. You can use a bank card or credit card.


Epic are gleefully slopping out a new client. Is that theft, Tim?

Weird how this stuff only applies when it's not you doing it.


If that were the case, they'd have done something about it before. This doesn't appear to be new.


Hopefully the party learned something from Biden’s four years.


Fun fact, parties, and more importantly the people in them change and evolve over time. They aren't stagnant. For example, we see this with the Republican party which use to hold claim to things like law and order. But times change, and so do parties.

So just because something was a certain way 20 years ago doesn't mean it's still that way today. That would be CRAZY to suggest that.


They have "evolved" to the point there is no difference between them anymore


Yes, obviously they agree on everything.


Guidelines | FAQ | Lists | API | Security | DMCA | Apply to YC | Contact

Search: