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

  > My Sony died very quickly. My Apple's are on their way out.
same

i'll never buy those apple earbuds ever again; hundreds of dollars down the drain and more e-waste cause those batteries cant be replaced... and sony: charging 70 bucks for wired earbuds and the cover falls off after a couple months usage what the f... (ok rant finished)


  > A trip there to do… what?
to play golf, what else?

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


  > Automatically solving software application bugs
the other issue is "fixing" false-positives; i've seen it before with some ai tools: they convince you its a bug and it looks legit and passes the tests but later on something doesn't quite work right anymore and you have to triage and revert it... it can be real time sink.

  > Who’s going to verify all those tests?
why, the user of course

  > appropriately is a skill issue
or maybe its a ux issue?

maybe chatbot style interfaces are just an artifact of the medium?

people talk about setting up harnesses and feedback loops etc, but a lot of the ux is a frankly mess...


I find that chat is pretty good when you're describing what you want to do, for saying "actually, I wanted something different," or for giving it a bug report. For making fine adjustments to CSS, it would be nice if you could ask the bot for a slider or a color picker that makes live updates.

  > Given how much the typical Apple consumer skews left
idk, that might just be something people believe but i haven't seen any evidence of that... many right-leaning pundits are apple users; even rush limbaugh was a mac user!

  > repo will always win over documentation
it really does seem like this... also new devs are like that too: "i just copied this pattern use over here and there whats wrong?" is something i've heard over and over lol

i think languages that allow expression of "this is deprecated, use x instead" will be usefull for that too


I’ve written about that a bit here https://jw.hn/dark-software-fabric

AI gets a lot of big projects right if you give at all the tools to verify its own implementation if you can build a proper system to verify the solution it works astonishly good. Even Opus 4.6 judgement seems to be wrong most of the time on projects of my scale pre the validation layers.


  > If you need that, don't use AI for it.
this is the right answer, but many companies mandate to use ai (burn x tokens and y percent of code) now, so people are bound to use it where it might not fit

  > I use LLMs in the same way i used to used stack overflow, if I go much farther to automate my work than that I spend more time on cleanup compared to if I just write code myself.
yea, same here.

i've asked an ai to plan and setup some larger non straight forwards changes/features/refactorings but it usually devolves into burning tokens and me clicking the 'allow' button and re-clarifying over and over when it keeps trying to confirm the build works etc...

when i'm stuck though, or when im curious of some solution it usually opens the way to finish the work similar to stack overflow


opendoc remembers...

Nah it’s 2026, you have to have an MCP server.

"I'm a developer who hates your decision to kill that tech. Can you please talk about your shitty adventure before you became CEO of this company cause I want to embarrass you?"

Then Steve Jobs gives one of his most memorable statements about building good products while ignoring the taunt.[0]

I got your reference. Cyberdog!

0. https://www.youtube.com/watch?v=oeqPrUmVz-o


yes, haha, steve really showed he was ceo material there fr

for reference if anyone is interested in poor old cyberdog (and the meme reference): https://oldvcr.blogspot.com/2023/10/teaching-apple-cyberdog-...


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

Search: