DE version is available. Content is displayed in original English for accuracy.
Advertisement
Advertisement
⚡ Community Insights
Discussion Sentiment
68% Positive
Analyzed from 4767 words in the discussion.
Trending Topics
#apple#siri#more#app#don#model#lights#alexa#off#turn

Discussion (159 Comments)Read Original on HackerNews
Never underestimate the power of a bored programmer
Now that's an agent I'd use. Can we start with Siri for the terminal?$ Siri 'List the files in this folder'
“AI as a chat bot” has always been cool and fun in sci-fi movies, but it’s the least imaginative real world use for it. We need to move past it.
> $ Siri 'List the files in this folder'
Why in the world would I ever use this instead of just ‘ls’?
I've never understood this obsession with trying to invent the talking ship computer from Star Trek TNG. The purpose of the talking computer in the series was not to be a "cool 24th century technology advancement". It was a plot device to keep the story going and explain things to the audience. Having a voice conversation with a computer is terrible, imprecise, plodding UX. It's not a good interface, it's not a good invention, it's not good technology. Yet $billions are being spent to try to invent it.
The best example I can think of in favor of what you are saying, where the computer does kind of serve the story and helps the audience, is the episode where Doctor Crusher gets stuck in the warp bubble and she has a lot of conversations with the computer about what is happening. But even then, she is out of her element, needs a lot of help from the computer, and it seems more convenient to do so via voice than anything else. She still travels to different areas of the ship to carry out actions, even though she probably doesn’t have to in case. The computer is clearly at its best for simple actions and answering questions, even if it can do more. The characters understand that and use the technology accordingly.
Instead of quickly iterating to find how to take voice to the next level, both projects quickly locked in on whatever that was and became too costly to pivot.
I never needed it to add stuff to my Amazon shopping cart or interpret things I said as voice shopping asks, which was a terrible UX.
There were so many other daily frustrations and Alexa skills that were half baked and random frequently resetting or going offline. Another frustration was Alexa failing to recognize the magic incantation to activate a simple action in the day to day when skills had overlapping utterances.
I actually wished Siri had better HomeKit IoT products so I could switch over, but I just gave up out of death by a thousand cuts wearing me down over the years and do everything manually now. Privacy and surveillance was also a huge tipping point to make me bin all my Alexa devices. I digress…
and more often than not isn't reliable unless you have a midwestern US accent.
Siri wasn't good. It still isn't good. Apple hasn't delivered on its promises with it and that's why it's being replaced with Gemini.
cobolcomesback: "ls, granny"
Granny: "it said No such file or directory"
cobolcomesback: "no, that's... just write ls, granny.
Granny: "I wrote ls granny it said no such file or directory."
cobolcomesback: "just.. from now on... just write Siri 'list all files in this directory', granny"
Granny: "I wrote siri list all files in this directory granny and it told me all the files and then it also asked me who's granny and I told it and it said nice to meet you"
cobolcomesback: "SIGH"
The thing that nobody really realized is that setup is a big factor that isn't worth to a lot of people. For example, to turn off lights with Alexa, you have to do a whole bunch of setup that involves installing special lights, installing app, connecting the app to Alexa. Even though relatively this is simple, its just not worth the effort to a lot of people.
Amazon or Apple could easily overcome this by offering Alexa or Siri connected devices as incentive to builders building houses or apartments. That way, when you plug in Alexa in your new apartment, it can auto detect everything it can control including lights, thermostat appliances, e.t.c.
It already exists in macOS 27: fm(1)
It is an extremely powerful tool, but here are the basics:
https://developer.apple.com/videos/play/wwdc2026/334/
Google assistant on the nvidia shield left Siri in the dust years ago. Siri can't even chain basic commands in your smart home, it can't retain any kind of context (e.g. dim the lights...a bit more).
This was frustrating for me as it always prompted “who cares? Just turn off the lights.” As well as would drive my parents and other guests batty.
I guess you should be able to create a bucket of low-risk tasks that require zero authentication, like letting your guests turn off the lights. I do get why they are cautious, though, because in some cases this could be a security risk, like a burglar turning off lights from outside the home.
So, progress?
Any agent with the Home Assistant MCP hooked up can do it fine.
For major platforms: “iOS 10.0+ / iPadOS 10.0+ / macOS 12.0+ / watchOS 3.2+”
Maybe I’m misunderstanding what you’re missing?
I am waiting for this function to sort my folders
Example: "I can use AI to combine multiple PDFs into a single PDF."
Okay let me just install a tool to do that because the OS doesn't usually have it built in in 2026.
Oh, it's riddled with ads. Oh it's paid for. Etc.
It's the same thing with the recent opening of knowledge thanks to AI.
Before: search for recipe with search riddled with ads, find website riddled with ads cookies notification requests forced sign up and a million other dark patterns, then an entire fucking life story before the recipe.
Now: "find me a good recipe for pasta that uses the stuff I have left over from the party last weekend, I don't mind buying a few more bits".
On Mac select the PDFs in Finder. Right click on the selected files to bring up the context menu. Select "Create a PDF" from the Quick Actions submenu.
This works with PDF files and image files as inputs.
https://apfel.franzai.com/
https://youtube.com/watch?v=W63oJtX0dP8
"Dammit, Bobby! Turn off the dang lights!"
People have speculated that with FPGAs or even an ASIC you could take some smaller models we have today, turn the chip into essentially that model-as-hardware, and get some really compelling performance/power-usage characteristics.
At that point running a GOOD quantized Q8 model on a phone is not beyond the realm.
That's what I was hoping for with Taalas, ultimately ending up with a microsd-ish card that's hot swappable intelligence.
That arrangement will change, somewhat, later today.
The code for all of those things is there, but not enabled if for most iOS users. There's a non-zero chance this code is there for Apple to try and convince the EU to let them release a Siri AI, and then just like sideloading have some impossible-to-actually-use alternative path to make the DMA happy.
There's profit to be made by offering customers choices here, I'm sure Apple will be ready to scoop up all of those delicious slop dollars.
So many other actors in the industry would have just doubled down and follow the race to the bottom
This looks more like a participation medal, if at all.
Apple Intelligence was an outlier in how they historically operate. I mean they literally just put out a folding phone after waiting what, a decade, for others to perfect it first.
Almost everyone developing their own AI is doomed to fail. I would not be surprised that when the dust settles, Microsoft CoPilot and Google Gemini will be left standing while OpenAI and Anthropic fade away. They will get what they need and then throw them away.
"Embrace, extend, extinguish" is the same playbook for decades, and you can only do that when you make money. Yes, making money still matters and post-capitalism is a big fat lie.
Handle the query on device. If the device cannot handle the query, push the query to Private Cloud, If Private Cloud cannot handle the query, push the query to a third party of the users choosing.
Which is pretty much the same as what they announced a few years ago.
Apple underestimated the amount of time and work needed to get to work and really the only bit that I think changed is that Private Cloud (and possibly the on device model) is a white label Google model rather than being developed in-house by Apple.
It also requires a relatively complex distributed architecture.
I worry about how successful they can be with this approach, in terms of best user experience.
https://www.macrumors.com/guide/apple-command-center/
Mark Gurman seems to get extraordinarily accurate and detailed leaks. I wonder how Apple got this leaky. Pretty much everything about the Duo was known months in advance.
Maybe apple can even have something similar to MCPs for tool invocations of apps and publish it so all models can actually be trained to use that framework
I built an app that lets me run terminals on my MacBook. It’s a Next app so I can go to that website on my phone using Tailscale. It has a built-in MCP server, so I can connect it to ChatGPT and have it create terminal sessions, orchestrate terminal sessions, all that good stuff.
Down the line, I’d like to be able to connect it to Siri and just talk to my phone and it can control terminal sessions and projects that I’m working on on my laptop.
I've been using the new siri, and it seems more or less stuck in instant-answer mode, which gives really terrible answers with any provider.
I wish more people were talking about this, but if you can't crank up the models to extended thinking, the technology is more or less stuck at 2004 levels of usefulness.
With mobile devices especially where ideally models could be shared across several apps.
But this specific code I'd assume is targeted to comply with EU regulations more than anything.
OT:
Since I've moved to Spain my principal Apple account is still in my home country but I've made another one for local app-store (since some local apps aren't available if you're not in the Spanish store).
iPhone is acting really strange, I'm logged to my principal account for iCloud+ and anything and local App Store.
If I log back to my principal account, I loose HCE mode and my building NFC app stops working until I re-log in the Spanish Apple Store.
If I'm logged at the Spanish account, I loose Siri AI which is blocked in the EU...
Among devices worldwide, who has the most control? Apple
They don’t build AI themselves, but when it comes to device infrastructure that allows AI to operate, Apple is naturally the strongest
Just as Meta had tried to build their own ecosystem through Libra and things like that
Won't AI companies end up doing the same? But that attempt doesn’t seem like it would be easy
Apple now feels like a kind of Coca-Cola stock
I wonder what the margin on this stuff is for them:
https://support.apple.com/en-us/127901I like tinkering with this stuff, everything around me is a perpetual lab, so I have more than 5 cameras that I'd like to hook up to this. But I REALLY don't NEED or WANT 12TB or storage.
I want all of these integrations to be possible locally, without having to send my data to the cloud.
But I cannot. A lot of these nice integrations aren't offered for fully-local setups.
Ostensibly they'll activate this in the EU when it's ready. Given the current functionality, it looks ready (or close to being ready). My guess is it is ready and Apple is doing their usual negotiation tactics with the EU to see who blinks first.
This is not how politics works here.
The EU said “build it then we’ll tell you”, which is crazy.
The problem is not having Siri use different models beneath. That’s not what the EU wants. They want Siri to be replaced by Gemini/etc completely. Which fits with the DMA.
Apple’s proposal was for something akin to an agent that could gather the necessary data for the 3rd party AI to use. Because what they refused to do is let any other AI have unfettered access to everything whenever it wants.
So I suspect this is really for Apple’s benefit. I don’t think the EU would be happy if you could still use Siri, but it was grok underneath. Because that would still be Siri.
This is what Apple claims and I don’t think you should believe it at face value. The EU has an entire team working on negotiating the boundaries with gatekeepers. They have a vested interested in compliance. Apple’s claims don’t sound credible.
The DMA requires interoperability so it requires being able to swap out Siri - completely. Competitors would need to be first class components with full system access. Apple has a long history of anti-competitive action in iOS. For example, Apple doesn’t allow full system cloud backup competition. One must use iCloud or it’s impossible to back up an iPhone over the air.
I side with competition and choice. If people want to use something other than iCloud, or Siri, they should be allowed to do that with their own hardware.
EDIT: by broader I mean all apps the user installs on their phone.
I don’t think that would meet the requirements of the DMA. Would it?
Self promotion blog article:
https://braw.dev/blog/2026-04-06-mobile-os-as-agentic-broker...
Besides, the modern concept of "agent" is what, some year old? Bit fast to ossify stuff in the OSes already.
iPhone is different, one button hold on phone without touch the phone is arguably Apple's last and only moat.
This is not that. This is expanding the Extensions that you already have. You can look at it in your Settings already.
All of which is why EU users are being left behind on the new Apple Intelligence (for now).
Also given that PCC is just marketing speak for "Apple pinky promise they don't read or share the data", it would be nice to get an API with first class access to my own data. So tired of being locked it.
But it will never prompt you anymore, because Siri AI can handle that stuff now when it couldn’t before.
Whether you think it’s better or not is up to you. I do. I also found the version of ChatGPT it used to be worse than the one in the app.
This would’ve been useful during their bake off where they were trying to choose if they wanted to go with Google, Anthropic, or OpenAI. But even without that, they would absolutely not want to be in a situation where they had to redo everything to get off a bad partner.
I do not want my personal data or the queries against it to leave my network boundaries if at all possible. This should be a default option.
Make a Shortcut that will open your local voice assistant app of choice when you press the action button.
Apple is in the game of providing an application platform. Maybe in the future they will provide their own LLM.