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

Apple accidentally left Claude.md files Apple Support app

x.com

Post reply on HN
Print view View original

111–120 of 339 posts

Re: Apple accidentally left Claude.md files Apple Support app

#111

Post by coldpie »

Hendrikto wrote: post #102
coldpie wrote: post #70

Earlier quoted context omitted.

It's trending in that direction. If you want genuine conversation with humans, it's best to start looking for small, private communities that have and enforce LLM policies that align with your desires. Public social media is universally trash, don't waste your time there. I think HN is still worth visiting for now, but it's getting harder to justify spending time here with the quantity of garbage-quality LLM articles…

> HN is still worth visiting, but it's getting harder to justify spending time here I feel the same. Quality of both submissions and discussions have considerable decreased. It is still the best general purpose “aggregator” I know of, but it is not what it was. It is becoming more and more FotM hype and boring group-think. HN was great due to the breadth of unique, interesting, nerdy topics, most of which I would hav…

I dunno, it's tough. I hesitate to say HN is "getting worse," even if I agree with that in my gut. I think that gives rose-tinted glasses and nostalgia-bait. Rather, I think the community is refocusing around something that I find uninteresting. If you find LLM output to be dull, as I do, it's less and less a place for you to be. I try to push the community in more interesting directions by upvoting articles with actual technical content, but yeah it's being drowned out by the ho-hum LLM output that I'm not interested in, and that means I want to be here less.

Re: Apple accidentally left Claude.md files Apple Support app

#112

Post by footydude »

Cthulhu_ wrote: post #52
gchamonlive wrote: post #16

Earlier quoted context omitted.

I think it's the same reason why MacOS and iOS degraded a lot in terms of UX the past decade. The focus of Apple shifted towards hardware independence. The 2010s was marked by Intel's lazy product lineup, year after year pumping rehashes of older products, iterating on top of their 14nm lithography with increasingly minor improvements on its architecture until AMD overcame them. In the process, Apple's partnership wi…

It's one of the biggest and wealthiest companies in the world, but your comment seems to imply they have to pick and choose what they pursue. They really don't, especially if it's hard- vs software.

> seems to imply they have to pick and choose what they pursue. They really don't, especially if it's hard- vs software.

Money can often just be one part of the equation.

To do things well you also need - available & capable technical resource, suitable facilities, available & capable leadership and management (with engaging at the right level in the business) and a clear vision of what you're trying to achieve/working towards.

Given how Apple appears to operate, I wonder if a strong desire for senior management control/oversight over major developments means they (artificially) limit how many concurrent large-scale things they can work on at any given time?

Maybe not, but that'd be my guess.

Re: Apple accidentally left Claude.md files Apple Support app

#113

Post by infecto »

bakies wrote: post #104
infecto wrote: post #99

Earlier quoted context omitted.

I was looking myself and it appears only certain regions (Japan) have that option.

I'm in USA, on a Pixel Android.

Hah I missed the part you said Google. You figure a thread about Siri was talking iOS. Of course the configuration path is the same in android as ios!

Re: Apple accidentally left Claude.md files Apple Support app

#114

Post by hansmayer »

ramon156 wrote: post #14

Unrelated: Yuck. a lot of those replies have LLM smells. Do people love being a hollow puppet for LLMs to fill in? Have people lost their identity?

> Do people love being a hollow puppet for LLMs to fill in? Have people lost their identity?

The first question, answer is yes - most people live their lives mindlessly, with or w/o LLMs (think every idiot you knew 20 years go throwing in punch lines from "Friends" to sound "funny"), To the second question - most people have a twisted view of identity. It is supposed to mean something identifying you uniquely,but to the most people it means, identifying you as a member of a large group (nationality/political view/religion/major music genre you like). So, now when every proverbial Dick, Tom and Harry use LLMs to generate Confluence content with shiny emojis, what are the proverbial Emily or John to do? Of course, they will adopt this new identity - its who people are now - shallow, hollow puppets for LLMs to fill in. And to think of the irony - mother Nature perfected this super-efficient, low energy and highly capable thinking machine, each and every one of us holds in their skull. Its already put us on the moon once, before we even had a semblance of a functioning computer! And we choose to throw it away, for fucking what? Verbal diarrhea and pain inducing coloured walls of texts?

All so some retarded antisocial VC-funded "AI founder" can call themselves a tech visionary?

Re: Apple accidentally left Claude.md files Apple Support app

#115

Post by dawnerd »

ramon156 wrote: post #14

Unrelated: Yuck. a lot of those replies have LLM smells. Do people love being a hollow puppet for LLMs to fill in? Have people lost their identity?

And when Called out they’ll use some excuse like oh I use it to fix grammar or translation. No, it’s completely obvious they’re being that lazy. I’d rather read comments with mistakes than LLM slop.

Re: Apple accidentally left Claude.md files Apple Support app

#116

Post by naravara »

acdha wrote: post #34
stefan_ wrote: post #13

Earlier quoted context omitted.

Okay, but why is the Siri team sitting out transformers. I really wanna move past the „Dragon Naturally Speaking“ experience with a bolted on decision tree.

Who’s doing it better? I have yet to hear from a Google or Amazon user who has a transformatively better experience, and I think that’s why they haven’t jumped so far because they have hundreds of millions of users who have daily habits that they don’t want to lightly disturb.

It’s not “transformatively better” but it definitely involves fewer frustrations to interact with. That’s always been Apple’s main value proposition, you’re not getting the most cutting-edge stuff but you’re supposed to have something that “just works” not something that makes you go “GODDAMN IT!” when it inexplicably seems to fumble normal things.

So if you buy Apple products based on that value proposition it’s a big problem for Apple if they can’t seem to keep their brand-promise in this area.

Re: Apple accidentally left Claude.md files Apple Support app

#117

Post by DaiPlusPlus »

thrtythreeforty wrote: post #94
DaiPlusPlus wrote: post #73

Earlier quoted context omitted.

"objectively better" is a subjective statement :) My preference, however, is for a voice-control UX just like I get with my Amazon Echo and "classic" Alexa like I have been for the past 10 years I've been using it: I think I can best describe it as a "voice-driven command-line" just like your OS' CLI shell, which makes its interactions predictable, even if it means I need to "know" what commands are valid in a given…

Here's a question: I don't understand the gap between these LLM powered voice agents vs CLI coding agents, the latter of which are obviously useful and quite resourceful at getting something done when asked in plain English. Seems like an agent given 20-30 tool calls like "read_sms" "matter_command", and "send_email" would be able to work out what to do for things like "set the house to 72° and text Laura that I did…

> Seems like an agent given 20-30 tool calls like "read_sms" "matter_command", and "send_email" would be able to work out what to do for things like "set the house to 72° and text Laura that I did it."

Incidentally, a major headline in the news this past week was about a coding-agent that wiped its company's entire system, including backups; which the company's staffers were confident was utterly impossible (as it didn't have any access to that system), and yet somehow, it did[1] (the TL;DR is the agent randomly came across an unprotected God-tier admin API-key/token saved to a personal text-file in a filesystem it had read-access to). If an agent can do that with only read-only access to a company's routine/everyday storage area then there's no way I'm giving it the ability to deactivate my house's fire-alarms and security-cameras via Google Home/Matter/Thread/HomeKit/X10/OhFfsNotAnotherCloudBasedAutomationScheme.

[1] https://www.theregister.com/2026/04/27/cursoropus_agent_snuf...

Re: Apple accidentally left Claude.md files Apple Support app

#118

Post by wutwutwat »

rvnx wrote: post #79
worldsavior wrote: post #65

Earlier quoted context omitted.

That's why he said fake internet points.

These points might be fake, but they are far from being useless, and actually have monetary value. There is a market for buying and selling "aged" Hacker News accounts (3 USD 15 USD for ~500 points) and upvotes / downvotes By purchasing just ~300 karma points, founders can unlock an uplift of tens of thousands of dollars in visibility on the home page (clients and investors). So the LLM comments are not here just for…

If you're going to make a claim that there is a market for aged HN accounts you need to back it up with sources/proof, otherwise, you're pulling nonsense out of your ass

Re: Apple accidentally left Claude.md files Apple Support app

#119

Post by circuit10 »

ShyCodeGardener wrote: post #86
DaiPlusPlus wrote: post #73

Earlier quoted context omitted.

"objectively better" is a subjective statement :) My preference, however, is for a voice-control UX just like I get with my Amazon Echo and "classic" Alexa like I have been for the past 10 years I've been using it: I think I can best describe it as a "voice-driven command-line" just like your OS' CLI shell, which makes its interactions predictable, even if it means I need to "know" what commands are valid in a given…

Whenever I see one of these comments, it's always from someone that tried it at the start and then gave up because of a bad experience. And many times there are more people commenting back that this was essentially the 1.0 version and that the current 2.0 version is much better. So as someone that uses none of these products (old voice assistants vs. ai ones) it's really hard to evaluate if any of these anecdotes mea…

No matter how good the LLM features are, I just want to turn my lights on and off and check the time. A perfect LLM could maybe perform on par with a simple deterministic command system for these tasks, but not better. All an LLM does is introduce the possibility that a command that worked fine yesterday will randomly not work

Also, one of my first interactions with this Alexa+ thing was “how long is it until 8:45am”, one of only a few commands I use it for to work out how much sleep I’m getting, and it proceeded to ask me what the current time was… I immediately turned it off after that

Post reply on HN