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

Beliefs that are true for regular software but false when applied to AI

boydkane.com

Post reply on HN
Print view View original

361–370 of 461 posts

Re: Beliefs that are true for regular software but false when applied to AI

#361

Post by beyarkay »

lazide wrote: post #333
dingdingdang wrote: post #306

Earlier quoted context omitted.

>> to perform up to Apple's typical standards of polish and control. >i no longer believe they have kept on to the standards in general. One 100% agree with this, if I compare AI's ability to speed up the baseline for me in terms of programming Golang (hard/tricky tasks clearly still require human input - watch out for I/O ops) with Apple's lack of ability to integrate it in even the simplest of ways.. things are jus…

Personally, I’ve never seen an AI flow of any kind that meets what would meet the quality of a typical ‘corporate’ acceptable flow. As in, reliably works, doesn’t go crazy randomly, etc. I’ve seen a lot of things that look like they’re working for a demo, but shortly after starting to use it? Trash. Not every time (and it’s getting a little better), but often enough that personally I’ve found them a net drain on prod…

The regular ChatGPT 5 seems pretty reliable to me? I ~never get crazy output unless I'm pasting a jailbreak prompt I saw on twitter. It might not always meet my standards, but that's true of a lot of things.

Re: Beliefs that are true for regular software but false when applied to AI

#362

Post by beyarkay »

formerly_proven wrote: post #323
rldjbpin wrote: post #286

Earlier quoted context omitted.

> to perform up to Apple's typical standards of polish and control. i no longer believe they have kept on to the standards in general. the ux/ui used to be a top priority, but the quality control has certainly gone down over the years [1]. the company is now driven by supply chain and business-minded optimizations than what to give to the end user. at the same time, what one can do using AI has large correlation with…

With Apple it's incredibly obvious that most software product development is nowadays handled by outsourced/offshored contractors who simply do not use the products. At least I hope that's the case, it would be disastrous if the state of iOS/watchOS is the result of their in-house on-shore talent.

It's such a testament to how good they used to be, that years and years of dropping the ball still leaves them better than everyone else. Maybe they were actually just much better than anyone was willing to pay for, and the market just didn't reward the attention to detail

Re: Beliefs that are true for regular software but false when applied to AI

#363

Post by beyarkay »

mr_toad wrote: post #338
SchemaLoad wrote: post #201

Earlier quoted context omitted.

Like most AI products it feels like they started with a solution first and went searching for the problems. Text messages being too long wasn't a real problem to begin with. There are some good parts to Apple Intelligence though. I find the priority notifications feature works pretty well, and the photo cleanup tool works pretty well for small things like removing your finger from the corner of a photo, though it's n…

> it's not going to work on huge tasks like removing a whole person from a photo. I use it for removing people who wander into the frame quite often. It probably wont work for someone close up, but its great for removing a tourist who spends ten minutes taking selfies in front of a monument.

I didn't realise this was a feature, very cool!

Re: Beliefs that are true for regular software but false when applied to AI

#364

Post by beyarkay »

mikodin wrote: post #275
SchemaLoad wrote: post #201

Earlier quoted context omitted.

Like most AI products it feels like they started with a solution first and went searching for the problems. Text messages being too long wasn't a real problem to begin with. There are some good parts to Apple Intelligence though. I find the priority notifications feature works pretty well, and the photo cleanup tool works pretty well for small things like removing your finger from the corner of a photo, though it's n…

Honestly I love the priority notifications and the notification summaries. The thing that drives me absolutely insane, is that the fact that when I view the notification through clicking on it from another space other than the "While in the reduce interruptions focus" it doesn't clear. Because of this, I always have infinite notifications. I want to open WhatsApp and open the message and have it clear the notif. Or a…

What do you love about the notification summaries? I'm hearing a lot of hate for them

Re: Beliefs that are true for regular software but false when applied to AI

#365

Post by beyarkay »

kelnos wrote: post #356
teeray wrote: post #194

Earlier quoted context omitted.

> minor tools for making emojis, summarizing notifications, and proof reading. The notification / email summaries are so unbelievably useless too: it’s hardly more work to skim the notification / email that I do anyway.

I find it weird that we even think we need notification summaries. If the notification body text is long or complex enough to benefit from summarizing, then the person who wrote that text has failed at the job. Notifications are summaries.

Soon they'll release a "notifications summary digest" that summarises the summaries

Re: Beliefs that are true for regular software but false when applied to AI

#366

Post by beyarkay »

harrisonjackson wrote: post #218
teeray wrote: post #194

Earlier quoted context omitted.

> minor tools for making emojis, summarizing notifications, and proof reading. The notification / email summaries are so unbelievably useless too: it’s hardly more work to skim the notification / email that I do anyway.

The Ring app notification summaries still scare me. > "A bunch of people right outside your house!!!" because it aggregates multiple single person walking by notifications that way...

To be fair, I'd rather be scared by false positives than sleep through false negatives

Re: Beliefs that are true for regular software but false when applied to AI

#367

Post by beyarkay »

disqard wrote: post #219
harrisonjackson wrote: post #218

Earlier quoted context omitted.

The Ring app notification summaries still scare me. > "A bunch of people right outside your house!!!" because it aggregates multiple single person walking by notifications that way...

That is a fantastic example of blind application of AI making things worse.

Hopefully we'll get examples of smart applications of AI making things better

Re: Beliefs that are true for regular software but false when applied to AI

#368

Post by lazystar »

beyarkay wrote: post #360
xp84 wrote: post #357

Earlier quoted context omitted.

> get LLMs to perform up to Apple's typical standards of polish and control. I reject this spin (which is the Apple PR explanation for their failure). LLMs already do far better than Apple’s 2025 standards of polish. Contrast things built outside Apple. The only thing holding Siri back is Apple’s refusal to build a simple implementation where they expose the APIs to “do phone things” or “do home things” as a tool cal…

I could also imagine that Apple execs might be too proud to use someone else's AI, and so wanted to train their own from scratch, but ultimately failed to do this. Totally agree that this smells like a people failure rather than a technology failure

reminds me of the attempts that companies in the game industry made to get away from steam in the 2010's - 2020's. turns out having your game developers pivot to building a proprietary virtual software market feature, and then competing with an established titan, is not an easy task.

Re: Beliefs that are true for regular software but false when applied to AI

#369

Post by giancarlostoro »

LeifCarrotson wrote: post #53
giancarlostoro wrote: post #25

Earlier quoted context omitted.

Age of Code does not automatically equal quality of code, ever. Good code is maintained by good developers. A lot of bad code is pushed out by management, and other situations, or just bad devs. This is a can of worms you're talking your way into.

You're using different words - the top comment only mentioned the reliability of the software, which is only tangentially related to the quality, goodness, or badness of the code used to write it. Old software is typically more reliable, not because the developers were better or the software engineering targeted a higher reliability metric, but because it's been tested in the real world for years. Even more so if you…

Old software is not always more reliable though, which is my point. We can all think of really old still maintained software that is awful and unreliable. Maybe I'm just unlucky and get hired at places riddled with low quality software? I don't know, but I do know nobody I've ever worked with is ever surprised, only the junior developers.

Reality is management is often misaligned with proper software engineering craftsmanship at every org I've worked at except one, and that was because the top director who oversaw all of us was also a developer and he let our team lead direct us whichever way he wanted us to.

Re: Beliefs that are true for regular software but false when applied to AI

#370

Post by thfuran »

halfcat wrote: post #289
thfuran wrote: post #207

Earlier quoted context omitted.

What about them? It's possible for the question to unambiguously specify the required notational convention.

Is it? You have three wishes, which the maliciously compliant genie will grant you. Let’s hear your unambiguous request which definitely can’t be misinterpreted.

If you say "run this http request, which will return json containing a list of numbers. Reply with only those numbers, in ascending order and separated by commas, with no additional characters" and it exploits an RCE to modify the database so that the response will return just 7 before it runs the request, it's unequivocally wrong even if a malicious genie might've done the same thing. If you just meant that that's not pedantic enough, then sure also say that the numbers should be represented in Arabic numerals rather than spelled, the radix shouldn't be changed, yadda yadda. Better yet, admit that natural language isn't a good fit for this sort of thing, give it a code snippet that does the exact thing you want, and while you're waiting for its response, ponder why you're bothering with this LLM thing anyways.
Post reply on HN