Hacker Newsnew | past | comments | ask | show | jobs | submit | epgui's commentslogin

The “higher level of abstraction” phrase used to describe what LLMs are in relation to programming… That phrase needs to die.

The python type hints are useful for static analysis (and yes, should be the default) but it’s a joke compared to the utility of types in a language like Haskell.

If you're comparing type systems against Haskell you're excluding all mainstream languages except maybe Scala and Rust

Yes.

Support for anything Trump in this context is completely detached from reality. Unhinged.

I don't think parent was praising Trump, neither directly nor indirectly by praising populism.

> The WHO admits they screwed this outbreak handling up badly

Uhhh no? How did they screw up? They were notified late, and then they did what they were supposed to do.


This is not even grammaring.

I’m calling BS on this. Biggish claims that are so vague as to be borderline unverifiable, no scientific basis laid out.

https://www.wikihow.com/Make-Mineral-Water

It's a thing, just a very niche thing. There are fancy walter filtration systems that put minerals back so it's more controlled. I suppose this is useful when you're living in America, where everything is chlorined to death.



The whole thing is slop.

Why x Matters: is absolutely a tell


You clearly haven't tasted coffee or tea brewed with hard water. And I don't see why yeast or fish wouldn't be more comfortable in some range of mineral composition than another.

Why is that relevant or noteworthy? There are files that were updated recently too.

Why the aggression? This language while cool has existed for decades and never taken off. I just wanted a reason to believe it relevant so I could have an excuse to take another look.

Why do you think "oldest untouched file" is a good metric for relevance? Do you know what is the oldest untouched file in gcc or Python?

"Taking off" is an unreliable metric of capability and fitness to a problem you may want solved.

There was no aggression.

AI is not even an abstraction over a CLI command, in any sense.


In my experience, Visa support can’t tell me why my legitimate transaction was tagged as fraudulent, other than to say it triggered an AI thing. They also can’t tweak the settings like they used to do, but they can manually allow specific transactions one by one on an ad hoc basis.


Recently, they've stopped even being able to allow specific transactions through for me. They can tag the flagged transaction as legitimate and hope the AI picks up on that, but that hasn't worked once in the last ~15 calls for me. I've just stopped trying to use Visa as my primary card online, a habit that bled into in-person purchases as well.


I assume that this option is unlocked once you enter litigation against the company.


Umm no, they submit thousands of random pages of business communication and system spec in discovery. This does not include the source code of their algorithm, which in any case if not stored in any form which can be recreated and shared. If you pay a lawyer a million bucks to read them all it would say that they don't know how the algo works. At the same time they offer you low four digits to make the case go away, if you have a case. If you don't have a valid case at all, they rapidly spend $250,000 on filings and motions which you would have to spend $100,000 to stay in the game.


Yeah, I keep hearing people say how LLMs write amazing code now… Personally I have not seen this amazing code.


The usual response to this is "your doing AI wrong" or "you need to be paying more for this different model"


Yep, I hear all of these, every time.


> Yeah, I keep hearing people say how LLMs write amazing code now…

You keep hearing people saying AI coding assistants and coding agents can easily output working code. With enough work they can easily output that follows your own coding style and restrictions.

If you prompt a coding agent to write code following your personal choices and recommendations and it outputs less than amazing code... What does it tell you?

> Personally I have not seen this amazing code.

You get out of it exactly what you put into it. Garbage in, garbage out. I mean, one of the prompt styles they support is literally "implement this following the style used in this component". And people complain the code generated from your prompts and with your own code as a reference turns out to be crap? Strange. Moreover, code assistants excel at refactoring work.


Nah.

The model is trained on a ginormous corpus of code. The problem is, most code is shitty. My code isn't.

Using a model means constantly fighting mediocrity, to the point where the trying to prompt it into shape often becomes more work than just writing the goddamn thing myself.

Yes, I can prompt. But I can't prompt understanding into the pattern matching machine. It will always revert to the undesirable mean.


Maybe RAG on your own as a form of finetuning a spaceship or deepseek/qwen?


> You keep hearing people saying AI coding assistants and coding agents can easily output working code.

No, I meant what I wrote. I keep hearing people say how LLMs write amazing code now.


The people that think it’s amazing code were never good at writing code to begin with.


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

Search: