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

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.


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.

Isn't viewing others chats sessions and decisions just a poor man's ADR with way more (too much) noise?

Yeah it is really, never thought about it like that!

Even a slopped up ADR would probably be more useful than direct access to chats.


The whole affair circus to distract from the export control circumvention is another example of "It's a big club and you ain't in it". In which you is all of us non billionaires.

The difference is that every PR is still heavily scrutinised for correctness. Companies are moving in the direction of LGTM reviews.

wait for the Looks Good To AI trend.

I've noticed they also love to write jest/vitest exhaustive input cases when one will do the job.

Sounds like constant shotgun surgery.

This is like saying the design of your mobile operating system barely matters as all you use it for is to open Youtube and a browser. Design is everything when building a product people interact with.


I am getting increasing disillusioned by the number of peers I am seeing completely hand over their thinking to a tool. Agents are great, but if you can't explain to me how your PR changes a system and why design choices were made you are no longer an engineer.


Agreed. Used to be prevalent in the frontend world (now I think it's the only thing that exists seemingly), where programmers would copy-paste stuff from Stack Overflow until things worked, and when you asked "So why did this actually fix the issue?" they usually said "I'm not sure, but it works now, that's what matters". This seems to be standard practice across the entire stack now.

I've even wasted my time jumping on calls (requested by the other party) where after 5 minutes of conversation, it's extremely clear this "technical founder" doesn't even understand the basics of their own design and architecture of the product itself, even less the technical parts.


This seems more a product of the incentives we have in society, namely seeing the rich and wealthy on social media and then wanting that quick and easy. So many of those cases are not people with passion for the problem.

Good things take real effort, bring back the TLC!


> Good things take real effort, bring back the TLC!

Ain't no one willing to reward the real effort any more. I take pride in not using LLMs beyond the capability of IntelliJ's advanced autocomplete, but then again, I only code for fun these days given I fled IT for electrical engineering.


> Ain't no one willing to reward the real effort any more.

A product of the times we currently live in, but which can also be changed.

This is a recent Michael Sandel talk I watch that has my brain gears turning on this subject

https://www.youtube.com/watch?v=Vp5qsEuUOWo


What we don't want to do is mirror the partisan political environment in the Ai yay, nay, or how. We need to be able to talk to each other in understanding and a shared reality of facts. Too much hyperbole right now, starting from the top of the big US labs. They need to step down a few ego and sycophancy pegs


Rule 2 security went out the door months ago. Nobody seems to give a shit that all unmonitored agent runs hit the trifecta.


This is a problem which is entirely solvable by existing and new design/production apps. Instead of working entirely with raster image agents should programmatically edit the target file format.


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

Search: