I think you might be fooling yourself with AI • Hacker News Board

Re: I think you might be fooling yourself with AI

#101

Post by dd8601fn » Thu, Jul 23, 2026, 4:45 PM UTC

foxyv wrote: post #51

dd8601fn wrote: post #4

Earlier quoted context omitted.

I just spent multiple evenings talking through a small data model. With the massive number of misses the model had, I can’t imagine how bad it would have been if I had let it yolo the first design of its choice, to build on. The requirements didn’t really change, opus just couldn’t see all the real world potential issues with its various suggestions. But it was helpful for me to talk it out. So I guess it fell in the…

I've found that my requirements and acceptance criteria are much less clear than I think they are. AI reveals when you are being too vague, almost instantly sometimes.

They always are. When you think you’ve got it all… ya don’t.

Unfortunately this recent experience wasn’t that as much as it producing rapid-fire misses when it did have the constraints. It regularly just violated X to kinda-solve Y. Or made up a solution to both that solves neither. And this wasn’t some wildly complicated scenario.

Sure made me solidify some opinions (we ended up pretty close to where I had started without it), but woo-boy… it was a painful journey.

Re: I think you might be fooling yourself with AI

#102

Post by ChicagoDave » Thu, Jul 23, 2026, 4:50 PM UTC

tempfile wrote: post #54

ChicagoDave wrote: post #29

These people keep citing that survey from 2025. That kills all arguments from the article instantly. December 2025 through today GenAI has become massively better. I’ve built things with Claude in contracted spans of time that would have been man-years in the before times.

>> although participating developers felt they completed tasks faster using AI, they where around 19% slower > Maybe that was true in 2025, but it's clearly not true any more - I feel so productive now! Even if you are right, this is a completely baseless argument. The people in the study felt the exact same way! And "it's 6 months old, so I won't listen to it" is an insanely high standard. You're eliminating all the…

That study…I would have agreed with the group at that time. Up until December, I was vocally skeptical that GenAI could be used for anything more complex than a “departmental” app.

Opus and similar models completely invalidated that skepticism, especially when context windows increased.

In the last two weeks I designed and deployed a new programming language that compiles in a browser. Impossible in the before times.

Re: I think you might be fooling yourself with AI

#103

Post by louwrentius » Thu, Jul 23, 2026, 4:51 PM UTC

pentaphobe wrote: post #65

The responses to this post made me really sad. Sure - it was light on the meat, But it's an opinion blog post, not a full article. the author ventures to cite their refs, acknowledges potential bias.. way more than you get with a tonne of front page articles (many of which probably should have been short opinion pieces like this) Sure - it's not particularly notable or high entropy enough to save, but it's far from o…

Thank you.

Re: I think you might be fooling yourself with AI

#104

Post by louwrentius » Thu, Jul 23, 2026, 4:52 PM UTC

hsuduebc2 wrote: post #30

These AI sceptics always omit the possibility that running LLMs could become much cheaper in the future, which it almost certainly will. This is largely an infrastructure problem, and it will be solved just as similar problems were solved with storage, network capacity, and computing power. There will be bankruptcies, but the technology will prevail, just as the web did after the dot com bubble. Personally, I see the…

This mostly reads like wishful thinking about the future, that's not a basis to make decisions on right now.

Re: I think you might be fooling yourself with AI

#105

Post by Aurornis » Thu, Jul 23, 2026, 4:56 PM UTC

eudamoniac wrote: post #98

Aurornis wrote: post #91

Earlier quoted context omitted.

> That there is no evidence (not personal anecdotes but the numbers) of productivity increase? The blog tries to cite a 2025 METR study as evidence of no productivity increase, but they ignored the newer 2026 study by the same group that did show a productivity increase with the newer tools. I also think it's funny that there have become these hard demands for studies and proof of increased productivity. We never saw…

Because those tools were adopted organically by users because they were obviously good. AI is pushed from leaders onto users despite the users not thinking they are good. If my boss decides the whole company is switching to emacs I think he should have some evidence to support that decision, yes.

> AI is pushed from leaders onto users despite the users not thinking they are good.

Developers are pushing companies to give them access to AI tools and increase their token budgets.

Re: I think you might be fooling yourself with AI

#106

Post by kelseyfrog » Thu, Jul 23, 2026, 4:58 PM UTC

amarant wrote: post #58

kelseyfrog wrote: post #15

Earlier quoted context omitted.

It's like looking at the popularity of sports betting and concluding that it's a viable way to make money.

And it is? Look at kindred group for example, they made >700 million GBP last year. seems viable enough to me!

To clarify, I mean for the bettors.

Re: I think you might be fooling yourself with AI

#107

Post by louwrentius » Thu, Jul 23, 2026, 4:59 PM UTC

lordnacho wrote: post #59

Zitron might be right about the economics of it, maybe it really does come crashing down. But we won't be forgetting about it. Even if AI stopped progressing today, it will still be massively, undeniably, insanely useful. I could use current models forever. LLM does things for me that couldn't be done in 2023. I don't want to go back to a world without it, but I'm also ok with progress stalling right here. As for the…

Taking your anecdotes at face value for a moment (which I should not), how does this benefit of AI you describe justify the nearly 1 trillion dollar investment?

Do you think that your perceived increased productivity offsets the true, unsubsidised cost of AI?

Re: I think you might be fooling yourself with AI

#108

Post by timmmmmmay » Thu, Jul 23, 2026, 5:09 PM UTC

tempfile wrote: post #54

ChicagoDave wrote: post #29

These people keep citing that survey from 2025. That kills all arguments from the article instantly. December 2025 through today GenAI has become massively better. I’ve built things with Claude in contracted spans of time that would have been man-years in the before times.

>> although participating developers felt they completed tasks faster using AI, they where around 19% slower > Maybe that was true in 2025, but it's clearly not true any more - I feel so productive now! Even if you are right, this is a completely baseless argument. The people in the study felt the exact same way! And "it's 6 months old, so I won't listen to it" is an insanely high standard. You're eliminating all the…

what evidence? more than half of social science studies fail to replicate, why would I believe that this one is in the good half?

Re: I think you might be fooling yourself with AI

#109

Post by korse » Thu, Jul 23, 2026, 5:09 PM UTC

>I'm quite influenced by Ed Zitron's reporting. And I'm also standing by my own idea that AI will run out of money and just be turned off due to the huge operational cost.

I wish this were how things are going but Uber is still surviving. I figure at least one AI company is going to come out of this alive and kicking.

Re: I think you might be fooling yourself with AI

#110

Post by solumunus » Thu, Jul 23, 2026, 5:11 PM UTC

eudamoniac wrote: post #100

solumunus wrote: post #71

Earlier quoted context omitted.

I feel sorry for anyone who isn’t experiencing the gains I’m experiencing. I can see why AI could suck in massive teams, or software with very messy and inconsistent architecture. As a 2 man developer team working on a mono repo with clear and simple architecture, consistent schema conventions, and heavy context available, it’s becoming ludicrous how fast we can pump out stable features. We must be 3-4x faster at thi…

>pump out stable features >data corruption...urgent fix required Do you people hear yourselves?

Are you claiming you’ve never been responsible for a bug that caused data corruption? Perhaps not, but it’s hardly a novel post-LLM bug. It’s regular stuff and obviously you know that.