Siri was the first widely available AI bot but they forgot to open it to developers. The ecosystem would have grown a million fold in all these years
Never underestimate the power of a bored programmer
Siri turn on the lights
Siri code a Doom clone in Swift
Siri design a landing page for a Consulting Agency
Siri summarize the latest news about AI
Siri find a solution to the Riemann hypothesis
Now that's an agent I'd use. Can we start with Siri for the terminal?
Amazon did exactly this with Alexa skills and it hasn’t exactly been a booming success. Turns out that all of the things you listed as examples are stuff that most consumers don’t actually want or will use.
“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’?
> Turns out that all of the things you listed as examples are stuff that most consumers don’t actually want or will use.
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.
Disagree. The TNG computer was used via voice input when it was efficient to do so, which is exactly how it should be. There were plenty of computer consoles, laptops, and tricorders/phone-like devices that were also used, especially with certain types of tasks. The crew could technically fly the ship and fire weapons via voice commands, but that only happened occasionally, in situations where it made sense. Also, when Picard wants to record himself playing a musical instrument, saying “Computer, begin recording” is simply convenient. It serves no purpose to the story or explaining anything to the audience. It’s just a tool. One that I would very much like to have.
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.
You should check out all of the voices available on macOS. They still have the original, robotic sounding MacinTalk voices from 1984, such as Fred. They’re fun to play with.
Personally, I think Majel Barrett is my favorite computer voice of all time.
You don't have to do it all the time as your primary interface.
My wife asks Siri questions all the time while she's busy.
"Siri, what's the time?", "Siri what will the temperature be in four hours?" etc.
It's not "terrible", it's pretty smart.
Alexa's big issue for me was that you had to remember very specific commands and unless you remembered the exact syntax you were out of luck. I genuinely think if the AI had been better and had been able to interpret commands better, skills would have been infinitely more useful.
Amazon and I guess Siri's original design was completely undiscoverable. Both had limited vocabulary and actions you could take. I had to learn from others what I could even ask the devices. Also both were audio only and for things like, "turn on the lights" that required talking to cheap 3rd party devices that barely stay connected, it was frustrating.
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.
> “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.
Most consumers don't understand the possibilities of this technology. They have been trained their whole lives, starting with K-12 government school that they work within the boxes they are given, that they do what they are told to at work and stay within the box, that Windows computer is a box they work within and cannot really change, that the iPhone they have has limits that they cannot go outside of, the apps they use, etc, etc.
The concept of "I use this app daily and I love it but these things bother me, so I'm going to ask Claude to find the source code, and build in the features and then push the new app to my phone" is something that doesn't even cross people's minds of 95% of the population. It's currently a niche thing that's being taken advantage of by tech nerds that live in the space, but it will slowly trickle down to more of the population over the next decade.
I think you have the wrong conclusion with Alexa’s skills and ecosystem, as a prior heavily bought-in Alexa user myself. It did feel like magic in the beginning and was a quality of life improvement if you automated repetitive task of daily life e.g. auto light/thermostat activation.
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…
> Turns out that all of the things you listed as examples are stuff that most consumers don’t actually want or will use.
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.
The problem with Alexa is that by the time it appeared anywhere other than Echo devices, it was already deeply enshittified. Siri is in your pocket, on your wrist, and in your ears. Alexa was stuck on your kitchen counter asking you if you wanted to try Amazon Music.
Granny: "cobolcomesback, what's that command I have to write in this black box thingee to list all the files in this folder"
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"
It is an extremely powerful tool, but here are the basics:
# Ask the default on-device model
fm respond 'Explain this shell error in plain English: permission denied'
# Start a conversation
fm chat --instructions 'Let's talk about economics.'
# Use the larger Private Cloud Compute model
fm respond --model pcc 'Are zebras and horses related?'
# Pipe stuff to a model
echo 'What is Swift?' | fm respond
I'd settle for a siri that can at least turn the lights off properly.
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).
Just today running latest developers beta, I asked Siri to turn on the coffee machine and it started playing some song instead. I found out later that I had named the switch coffee machine plug.
Similar thing happens when I ask Siri to play my favorite songs and it starts to play a song named favorite from my library
I gave up on using Siri for my lights because 1/3 of the time it would get caught in a “who is speaking? Please go through the voice configuration to identify yourself.”
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.
> This was frustrating for me as it always prompted “who cares? Just turn off the lights.”
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.
Siri is Gemini now (Semeni?) so expect similar stories from both major phone OS providers going forward, since we have lost more diversity in the mobile market (seems anti-trustworthy to me)
I hate to do this, but I decided to "search" google for "gemiri" just to see, and was presented with
---
AI Overview
The term "gemiri" is relatively rare and can refer to a few entirely different things depending on the context.
Tech Slang (Gemini + Siri): It is a modern, informal portmanteau used by tech enthusiasts on social platforms like X (formerly Twitter). It describes a hypothetical or user-modified pairing of Google's Gemini AI with Apple's Siri assistant.
Medical / Cancer Regimen: In oncology, GemIri is a shorthand medical code for a combination chemotherapy regimen consisting of Gemcitabine and Irinotecan
I tried "turn off the lights in [room a] and [room b]" in the new Siri app and rather than Siri saying they can't do compound commands they just turned off the lights in one of the two rooms listed.
So, progress?
Any agent with the Home Assistant MCP hooked up can do it fine.
$ Siri 'rename this thousand of photos in these folders describing their content and make sure to use the same name for duplicates regardless of their size'
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".
> Okay let me just install a tool to do that because the OS doesn't usually have it built in in 2026.
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.
Yes and even further, Apple added an LLM into iPhone 17s and higher but their terms of use forbid a wide number of categories of queries on it. Which means it can’t be prompted directly by any users.
The thing is, Apple will have never lost this opportunity. The distribution advantage of the user base is so deep they can basically always implement this at will.
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'