It's always frustrating but never particularly hard to find the special incantation that will invoke it to do the thing that you want it to. Overall though it's simply not worth the effort which is probably why I end up using these overwhelmingly complex devices only for their most mundane functions like timers and getting the weather.

Trying for anything moderately complex, and I might as well be asking the dog to do it for me.

For example I have Philips Hue lights behind the TV/Screen on my living room wall, and I use their "color loop" behind the screen when watching movies etc. The problem is that "TV", "Television" and "Screen" are semi-protected words, so "turn off tv lights" ends up with the TV being turned off 9/10 times. "We" compromised and those lights are now called "screen wall" lights

As for setting certain lights to "the color loop", what used to be a 90% success rate (the other 10% turning my lights to "the color blue/bloo(p)") will now set the lights of the room I'm currently in to the color loop, which is usually the living room, not the screen wall. Also as recently as this summer I used to be able to set the whole house to "the color loop" this feature recently disappeared. The color loop slowly and nearly imperceptibly fades the colors from red to green to blue etc over several minutes. It's technically part of "hue labs" but it's a "beta feature" that's been available in the product now for over three years so I would argue it is core functionality at this point.

Because coffee is for closers.

At least there are no tribbles.

I used to be able to ask Siri: "Hey Siri, please set the lights to green." Then she would obediently set all of the lights to green. Nice, that's my favorite!

Then a few months ago some update was pushed (iOS? Apple Home app? Philips Hue app? Philips Hue Basestation OS? No idea) and now that exact phrase (which has worked for two years) suddenly elicits a response: "OK, which room?" -- followed by a listing of the rooms in which I have devices and a catch-all "Everywhere".

So now I've had to change my incantation: "Hey Siri, please set all of my lights to green."

I'm just waiting for her to start asking "Do you want Lime Green, Aqua Green, or Vomit Green?". Or worse, maybe she'll just give up and say "OK, here's a list of Google results for Green Lights." Maybe even throw a captcha in there asking me to select the green lights at intersections, just for good measure.

I have an iPad with iOS12, and when I say “turn off the lights”, all the lights turn off.

I also have an iPhone with iOS14, and when I say “turn off the lights”, she asks where. Super annoying.

/s

Actually, I set my living room to red because that's my favorite. And I set my dining room to blue because eating is cool. And when you gotta go then just look for the green light in the hallway in front of the bathroom. And my office is definitely purple in the morning to show just how much I want to punch things because I have to work. It's pink in the afternoon because pink noise from the freeway shouldn't be limited to sounds.

At night I set all the lights to 15%. With the colors it's dark enough to not be blinded when I want some water from the kitchen but also bright enough to see the contours of the door knob or kitchen table or dining chair so I don't stab myself with any of the corners while walking blind.

What colors do you set your lights to?

For working during the day, my office lamp is "banana mania". For dinner time, the dining room lights are "topaz".

You can also set a light to a color manually, then ask Siri what color it is. (This is how I discovered "banana mania" which is Siri's name for the color Hue calls "concentrate".

Never even thought of this. That's modern day software discoverability for you

I have some colored lights from Eria that have about as good color spectrum and integrate with Zigbee base stations. They were about 1/2 the price of Philips Hue. But the downside is that they don't integrate with Apple Home. Apple Home (and Siri) only recognizes the expensive Philips Hue lights even though the Eria ones are connected to the same Philips Hue base station. So with the Eria lights I just change the colors manually with a third party app on my phone.

And as a bonus as a developer: Philips Hue has an API to work with the devices connected to the base station. It's super fun to tell coworkers about a script that sets my lights in the office (and visible in video meetings) to red because the server in the living room is having trouble. ;)

> [...] this device will be free from defects in material and workmanship and will operate for 2 years and 3 years for Energy Star certified products, unless a different period is stated in or on the packaging of the product, based on up to 3 hours average working time per day/7 days per week, when used as directed

I don't really know anyone who only uses lights three hours a day, especially when it gets dark pretty early during winter.

[0] https://www.philips-hue.com/en-us/support/legal/warranty

For more generic lighting, there's a reverse engineered firmware you can load onto a ZigBee. I used them to create some wake-up therapy lights: http://edwardsh.in/2019/07/22/hue-compatible-therapy-lights

But I already have a grocery list and a process for it. I just want a reminder to add something to it.

"Hey Siri, set a reminder <for {date/time|location}>."

> "Okay, what do you want me to remind you?"

"Put dingus on the grocery list"

> Done.

“Hey google, dinner time “ - shut all lights but the kitchen and start a playlist.

“Hey google, tv time” - set all lights to specific colours and turn off any music.

If these things would actually work, I'd definitely use one regularily. However, whenever I visit an Alexa owner, I realize after a few interactions that I really couldn't be bothered with this stuff.

I think the "taxi" problem is still around with Siri. Put any taxi organisation into your phonebook, and include "taxi" in the name. You will likely not be able to call it with siri, since it insists to search for taxis in your area. Its always the same bug. These things have absolutely no idea about the context. And some hand-crafted rules go haywire after a while, because apparently nobody reviews them. When I got my first iPhone (iOS 5) I put in my date of birth during configuration, and promptly noticed that the german speech synthesizers says Nineteenseventynine when I enter 1979. All aother 4-digit numbers are fine, only 1979 is pronounced english. So apparently someone put this exception in there for a completely bogus reason, and it stayed there. It is still there today, after 8 years.

Because they’re currently better than nothing. My HomePod works 90% of the time. I can create specific scenes for the things she can’t quite figure out.

Being able to walk in to the kitchen and tell her to put the radio or the light or a specific album or a timer on is actually really amazing. Most of the time. Certainly amazing enough to suffer the times she doesn’t want to co-operate, because then I just do that myself which I would have done anyway.

It helps that the HomePod is also a great speaker in its own right, and that it’s one single cylinder with one cord. It’s a very tidy device.

The only use case I see which has an acceptable failure rate is asking for the time and setting a timer. And even asking for the time fails about 1/10 times with the Alexa system my gf has in her flat...

And if asking for the time is the only thing which works decently, well, that is really telling about the state of the art...

Why not?

Why not?!

not always. I used to use google play music to play music from my own library in the car. any time I asked it to play a moderately obscure artist, it would interpret that as whatever popular artist had a similar name. it would then play the radio station for that artist, since I didn't have the premium subscription. I found some success with spelling out the artist name letter by letter, but even that consistently failed for certain names.

also sometimes I would say "list albums by X" to help me remember the name of what I wanted. no matter what I tried, it would only list three albums "and others". who could want this behavior? if I ask you to list albums, yes I actually want to hear every single album name!

I'm now paying for YT music (since the free version apparently does not support android auto), and it so far it works flawlessly. infuriating.

I think magical incantations is a perfect way to think about it. Using voice assistants feels more like the land of Harry Potter than the land of technology we live in. It's the flipside of “Any sufficiently advanced technology is indistinguishable from magic”.

Similar story for self-driving cars: car driving helpers/assistants (lane keeping, etc.) are ok, self-driving cars will be a huge disaster until we are really close to AGI.

These are the things where getting 80-90% there isn't enough. We're smarter than chimps or other animals because we can cover the long tail of events.

Meanwhile, here in Siri Land...

Me: Hey, Siri, add "tomatoes" to my Groceries list.

Siri: OK, Reapreducer. Which list should I add it to?

Me: Groceries.

Siri: OK, Reapreducer. Which list should I add it to?

Me: Groceries.

Siri: OK, Reapreducer. Which list should I add it to?

Me: Groceries.

Siri: OK, Reapreducer. Which list should I add it to?

Me: Groceries.

Siri: OK, Reapreducer. Which list should I add it to?

Me: Cancel.

I've gone back to paper grocery lists. They Just Work™.

That said Siri feels at least 100 times smarter than Google assistant to me, the below are actual (if somewhat anonymized) examples:

- Google suggestions when I look at the phone at 5am in the morning: "text random friend of a friend that I answered a question for over Telegram" or "call customers project manager". See https://erik.itland.no/tag:aifails for screenshots and more examples. In the years I had access to the future it maybe helped me twice by pointing out it was time to leave for an appointment.

- Siri suggestions are mostly mundane (more or less predictably tells me when to leave for appointments, kids soccer and hockey training etc, suggests picking up kids at kindergarden - although not consistently, suggests sending messages to my wife over our preferred messaging solution, tweeting, or if I drive 5 minutes down to the shopping center: that I should drive home the way I always do etc) but I have never caught it suggesting outright idiotic things like Google, and once this weekend it even suggested something semi-smart (a text message to my wife that was surprisingly close to one I could have written myself to tell her I was on my way home, including one of my rather unusual abbreviations and with good timing :-)

TomTom had this solved eons ago - my TomTom 5000 from 2014 automatically sets destination as work when I get in the car in the morning, and home when I'm done with work. And it learns my schedule per day, so it doesn't do that on the weekends, or if I need to pop out somewhere at lunch. Such a simple feature from 6 years ago works better than anything that Google can seemingly come up with.

Almost 30 years later, how many orders of magnitude faster silicon and countless person-hours of research and I can't get my damn phone (which, yes, _is_ a marvel that way-back-when-me wouldn't believe) to recognize, "call mrs_mynameisash" when I'm using my hands-free while driving. I don't know how many times Google's voice assistant has called some (possibly local?) T-Mobile instead. And my wife's name sounds nothing like "T-Mobile".

„Thank you... delete thank you“

https://www.youtube.com/watch?v=MzJ0CytAsec

I remember, when I was a wee little lad back in '96, playing on an old Mac Plus with a black and white screen. Even then we had software installed that would let us control the old Mac Plus with our voice. It was the first time I'd ever used a boom microphone.

Here, go reminisce: https://en.wikipedia.org/wiki/PlainTalk

My dad insisted that a boom microphone was required -- not just any microphone but a "boom" microphone specifically. It was interesting when I showed him some smaller microphones years later that worked better with less noise.

Oh man have I grown since. Hardware and processing power have both grown so much. But speech recognition is still as dumb (or even dumber) as it was 30 years ago. It certainly didn't need the internet to work back then!

Also Siri is constantly having problems knowing if I’m talking to my watch or my iPhone, even if my phone is in my pocket.

Perhaps it was just being passive-aggressive?

Funnily enough, this is one issue I don’t have: between my phone, watch and iPad I’m consistently impressed at how well it manages to choose the best one - does anyone know if Apple devices actively co-ordinate which one responds to Siri commands?

Me: Ok, Google. Remind me to leave at 1 O'Clock.

Google: Ok. Do you want to save this? <shows preview of reminder, dings to indicate it's listening>

Me: Yes.

Google: Shows Google search results for "yes" and tosses the reminder.

I say, “Add blood pressure <pause> 120 over 80 plus 60.” Then I use the shortcut to parse the string on the / and +, and record it to Health.

The hard part was finding delimiters that Siri would consistently record as a single character. That and realizing I needed a manual review step to make sure Siri didn’t happily pump garbage into my logs.

> Hey Siri, set a timer for 8 minutes.

> Ok. 8 minutes and counting.

I only figured out through trial and error that I can name my Alexa timers without waiting for it to prompt me:

  > Alexa, set a pasta timer for 10 minutes
  > - Pasta timer, 10 minutes, starting now.
  > Alexa, cancel pasta timer
  > - Pasta timer canceled

I can't speak for the chef, but it does on HomePod. Each gets its own name and that name is announced when the alarm goes off.

"bleep bloop bleepity boop! Eggs timer. bleep bloop bleepity boop!

It has for at least the past couple years now.

Hey Siri, set a timer for 5 minutes. "OK."

Hey Siri, set another timer for 10 minutes. "A timer is already running, do you want to replace it?"

If you miss hearing the distinction in the confirmation, you'll miss the scheduled event

Edit: They also have distinct classification of alarm/timers. You can use either word to create one but checking what you've set or trying to cancel will result in 'no timers/alarms' set if your request doesn't match their system design.

I do have to specify "Living Room TV", even though the speaker and chromecast are configured to be in the same room, it still just turns off a bedroom tv if I'm not specific about which tv.

Also "Hey Google, turn off the Xbox" works, because I linked that at some point.

So not just timers! ;)

The thing I use Siri most for is "Hey, Siri. Tell me a joke."

My dream job is to work at Apple compiling jokes for Siri to belch out on demand.

> Hey Siri, set a timer for 13 minutes

> 30 minutes and counting.

> Hey Siri, set a timer for thirteen minutes.

> oh you already have a timer running, do you want me to change it?

> yes

Also I have set timers and lock the phone ‘too early’ and the timer was lost

It used to do a cheesy "Starting your timer.... Now", which would have been okay if a bit tedious repeatedly, apart from the fact that actually you could see that the timer started immediately, so the whole delayed "now" thing was completely misleading. It was like that for well over a year until I noticed it was fixed just recently.

Siri: I couldn’t find a shopping list, do you want me to create one?

Me: no. Hey Siri, add tomatoes and grap-

Siri: you have to select which app you want to continue <shows 6 apps, including Paprika. I tap Paprika> Sorry, Paprika has not implemented this function yet.

Me: Hey Siri, addtomatoesandgrapestotheshoppinglistinPaprika

Siri: ok, I’ve added “tomatoesandgrapes” to the shopping list in Paprika 3

<phone flies out of the window>

I take a photo with my phone. It's not perfect because to mark things off you'd have to use the photo-editing on the phone which would be rather clunky for that purpose. But it works if you don't mind checking things off in your head.

> How do you keep it from getting erased?

I've got a glass whiteboard and use liquid chalk markers. It's tough to accidentally erase something with those.

Also fun - you say something, the words you said show up on the screen, and then change into completely different words.

Yep. When it works, I get entries for both "ginger" and "ale."

Voice Recognition Elevator - ELEVEN!

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

First aired in 2009

https://github.com/fredley/digital-black

I see that I still have no reason to bother, it's going to frustrate me more than anything else (especially with how downhill voiceover has gone in 12).

The latter point is a bit broader: now that Siri can hit an arbitrary URL via shortcuts, you can really just set your own trigger phrase to do anything that can be automated. You better believe I have a raspberry pi on order which will be running a local webserver...

Point is, YMMV; just try it for yourself.

https://news.ycombinator.com/item?id=25280410

I don't use any of these "assistants", but curious if you responded with "Groceries List"? Knowing they work on keywords, to Siri, you may not be actually answering her question.

1. I have my phone set up to trust bluetooth in my car and unlock my phone. I get in the car and say "okay google, open spotify" -- this is so that it will continue playing what I was listening to before I left work.

"Okay", she says, and then tells me that she can't do that because my screen is locked. Sometimes this works, and sometimes it does not.

2. When I had Google Play Music it reliably would play random sub-par covers of songs rather than the original, even when I specified the artist.

3. Sometimes it decides to rely on screen input instead of audio controls. I can't do that while I'm driving.

4. It sometimes ends voice input too early or does voice input inconsistently. I've sent messages to my wife saying "I'm on my way home exclamation point" instead of "I'm on my way home!"

5. Commands which have worked for months suddenly stop working.

6. Sometimes my screen stays on, forever, after asking to play music. (OnePlus 7T, Android 10). This does not always happen.

7. Google: "Here's your message, send it?" Me: Yes Google: Sits there for a moment and pops up the results for "Yes" in the assistant.

My biggest gripe isn't what it can and can not do. It is the inconsistency that drives me up the wall. I am not a heavy user and most of my requests are because I wish for it to be hands-free in a car with bluetooth audio. I'm sure that this is a harder problem to solve than just me interacting with the phone, but it is a common use case.

This is my biggest gripe. Whatever magic voodoo ML they use is inconsistent, and it's not clear what level of abstraction this inconsistency is happening in.

What I want is the reliability of Google Assistant's speech to text parsing, combined with a firm, customizable interface. Something like If This Then That, where there are some default commands with a clear reliable command pattern: "send message to George Orwell, we live in your book", and commands can be added.

I use Android these days, but have stopped even attempting to use voice control when driving for all the reasons you've mentioned. It does almost feel like the functionality has gone backwards in recent years.

Or, possibly different tires.

This is an unusual problem - sounds annoying in general!

This isn't great.

Part of the disconnect here is likely how I am understanding "Trusted Bluetooth Device". I likely have to unlock it once while paired with that BT device, while the text says "$DEVICE_NAME unlocks this device when nearby".

Ask for War Pigs? Here’s the live version

Ask for a Come Sail Away? Here’s a terrible cover

Ask for Magic Stick? Here’s an instrumental

I swear it just picks the version of the song that pays the least royalties and plays that instead of the right one...

This is a very interesting theory, I don't know if this was revealed somehow but considering how consistently terrible the guesses are on assistant devices... I wouldn't be surprised.

I think the far more likely explanation is just that these home assistant products suck.

Assuming the voice recognition part worked perfectly:

1) query song database for input 2) play result that is most popular (most plays by manual selection in eg desktop client etc)

The only tricky part is to determine whether the query is an artist or a title but again in most cases this will be solved by checking popularity.

What's a plausible explanation that they mess this up so badly?

Karaoke time! You can do this.

I am sure they're working on improving it. We've not yet reached late stage capitalism with voice assistants.

The thing is predictability, though, and maybe handling the common use cases. It gets frustrating when they get worse. Kids, on the other hand, only get better at understanding you (though perhaps also better at frustrating you on purpose).

To put it simply, I'm happy to make myself perform incantations. I'll say "Ok Google, grooblepuff the bonkman" to get the thing to do the thing. This whole thing has made me understand why wizards and sorcerers chant Accio! and Sectumsempra! and shit like that because if they just said "Bring me my firebolt" no one knows how the AI that runs magic in the world would interpret that.

And you know someone who feels this strongly about the product is pretty bought into it. Like, if I didn't use it so much, I wouldn't be complaining this much.

Relatedly, I wonder if these assistants “filter bubble” you like search does. Like, learning what types of things you are looking for and grouping you with other similar people.

Unfortunately, there was a tour going through the lab at the time. Some VPs from some company got to watch me honk the horn and then bang my head against the desk.

In the last 16 years, the state of the art has not advanced, as far as recognizing my speech goes. It still don't work.

The answer to any technical problem will present itself within 30 seconds (sometimes minutes) of asking "Hey, can you take a look at this?"

Cunningham's Law states "the best way to get the right answer on the internet is not to ask a question; it's to post the wrong answer."

The concept is named after Ward Cunningham, father of the wiki. According to Steven McGeady, the law's author, Wikipedia may be the most well-known demonstration of this law.

Cunningham's Law can be considered the Internet equivalent of the French saying "prêcher le faux pour savoir le vrai" (preach the falsehood to know the truth). Sherlock Holmes has been known to use the principle at times (for example, in The Sign of the Four.)

"If, instead, you say 'Linux sucks, you can't even get a f*&$ing WiFi driver working!' thousands of people will solve the problem for you."

Whether unintentional or not, it has put a huge smile on my face.

Or put differently, you are completely wrong about Sherlock using it in Sign of the Four. Prove me wrong! ;)

I watch a lot of YouTube on my phone when cooking, I even built a cardboard stand for my phone for this reason. What I want is for YT to respond to these voice commands:

- Pause video.

- Play video.

- Rewind 10 seconds.

- Skip the (expletive) ad <-- ok, I can understand why this one might not work.

Sadly, this doesn't work. And it's the only voice assistance I really need :(

[1] https://github.com/kalliope-project/kalliope

Was also curious about your use cases on the phone (aside from ad skip), and they actually worked for me. I'm using a pixel 4, though wouldn't think that'd make a difference.

OK Google, install Newpipe.apk

In classic Internet tradition, you basically need to setup a shadow Google account where you lie about their age and add them to your family account anyway. Thanks Google!

The "solution" is to cast the tab. Which means lower bitrate, no music controls, and if you cast to a display device, the whole tab screencasts etc.

I guess it's because nobody important uses the web anymore? Or something?

(Disclaimer: I work at Google. But not on YTM. Most Googlers I know have switched to Spotify, including myself.)

Even Gmail, can’t trust that it won’t be deprecated in the future.

Music-wise, I have completely transitioned to Alexa and Amazon Music. The interface is worse, but they seem to be more stable.

I just wish I could upload my own music and have Alexa connect to Bandcamp.

Leaving YouTube is nigh impossible.

any examples?

If you say "OK Google play my likes on youtube music" it will play `Your likes`.

If you forget the `on youtube music` part even if your default player is set to Youtube music it will play the `my likes` song.

My tolerance for mistakes for simple commands that work sometimes / are the right command ... but don't work is ultra low.

Like how is it my Android phone will default to just googling "exact valid voice command letter for letter" (it's used in a commercial for cripes sake!) ... and not somehow notice that?

Similarly, they say English language Search is powered by Transformers. But when I want to perform searches it often switches the intent to something wrong. It's a blunt tool, not a precision instrument.

With natural language and speech interfaces, we face such long tail problems too .. like the Burger King ad triggering a whopper lookup via "ok google".[1]

[1] https://www.nytimes.com/2017/04/12/business/burger-king-tv-a...

I start using it. I have two or three commands I do regularly.

One of the commands stops working. I stop using it forever.

I have to re-do it with "Ok Google, text Mary 'I'll be home in 10'", and growl a lot on the inside.

And on mobile GPM had a very simple functionality: a playlist containing all the songs you've downloaded offline. To the best of my knowledge YTM has no such thing, just a playlist _it makes for you_ of offline songs.

Also, the shuffle button only shuffles the current songs in queue, not the playlist your currently listening too like Spotify and GP Music do.

They couldn't move it to my main because it was legacy, but that was where I had youtube premium/red whatever. So then I needed to switch between accounts. Not fun while you are driving.

Oh then they stopped premium so I started hearing ads. Not what I want when I'm trying to calm my screaming kid in the car. Oh, and I need to keep my phone screen on.

Many of the songs aren't the same as on Google play.

Google seems to be moving toward search/email/YouTube. With few other products. Probably good, they can't handle it.

Inferior is much better than "we'll delete your music library on an undisclosed date in December".

Maybe not Apple because their fanatics will apologize for any wrong doing.

Wonder if these AI assistants will lead to the development of a new language.

Exterminatum Horix Abracadabra (Siri, play something nice).

What we need are people building interfaces for themselves, not people building interface they think are good for others.

I'm astonished at how badly it works compared to Alexa, but sadly, Alexa no longer supports alarms via BBC Sounds, so it's not an option for me.

When Bart, Lisa , Maggie and Marge were at the Mt. Useful Visitors Center, Bart went to a statue of Smokey the Bear. Smokey said "Only WHO can prevent forest fires ?" Bart then pressed the You button and Smokey said "You pressed you, referring to me, that is incorrect. The correct answer is you."

This used to really irritate me. Microsoft called folders things like “my pictures”. The awkward personalisation seemed so gross (I used a Mac). However Spotify’s “Your likes” is even worse, it sounds more like big brother giving me temporary access. I’m not sure how I ended up fixating on this.

That said, I end up frustrated with Alexa more often than satisfied.

I get the impression that many Google employees do not use the products they work on.

When they forced the transition to YouTube music, I gave up the service for good.

Now only Google can hear my every word via cellphone and Nest.

And look how incompetent Google is. I don't even get creepy suggestions on ads since I deleted facebook.

This is a question that I too ask myself daily with a lot of the software that I deal with and depend on.

But the way I see it is that any Google Assistant PM is going to see this for what it is: someone who is angry because they love not because they hate.