Introduction
Why does Google insist on making it’s assistant situation so bad?
In theory, assistant should be the best it’s ever been. It’s better at “understanding” what I ask for, and yet it less capable than ever to do so.
This post is a rant about my experience using modern assistants on Android, and why, while I used to use these features actively in the mid-to-late-2010s, I now don’t even bother with them.
The task
Back in the late 2010s, I used to be able to hold the home button and ask the Google Assistant to create an event based on this email. It would grab the context from my screen, and do exactly that. This has been impossible, as far as I can tell, to do for years now.
Trying to find the “right” assistant
At some point, my phone stopped responding to “OK Google”. I still don’t know why it won’t work.
Holding down the Home bar (the home button went the way of the dodo) brings up an assistant-style UI, but it’s dumb as bricks and only Googles the web. Useless.
So, I installed Gemini. I asked it to perform a basic task. It responded “in live mode, I cannot do that”. Asking it how I can get it to create me a calendar event, it could not answer the question. Saying instead to open my calendar app and create a new event. I know how to use a calendar. I want it to justify its existence by providing more value than a Google search. It was ultimately unable to answer the question.
Searching the internet, apparently both of the ways I had been using assistant features were the wrong way to do it. You have to hold down the power button, that’s how to launch the proper one. My internal response was:
No, that’s for the power menu. I don’t want to dedicate it to Assistant.
Well, apparently, that’s the only way to do it now, so there I go sacrificing another convenience turning it on.
Pulling teeth with Gemini
So I ask this power-menu-version of Gemini to do the same simple task. I tried 4 separate times.
First, it created a random event “Meeting with a client” on a completely different day (what?).
Second time it just crashed with an error.
The third time, it asked me which email to use, giving me a list, but that list did not contain the email I was interested in. I asked it to find the Royal Mail one. No success.
So, quite clearly, it wasn’t using screen content.
I rephrased the question: “Please create an event from the content on my screen”. It replied “Sure, when’s this for?”
I shouldn’t have to tell you. That’s the point. It’s right there.
Conclusion
There are too many damn assistant versions, and they are all bad. I can’t even imagine what it’s like to also have Bixby in the mix as a Samsung user. (Feel free to let me know below.)
It seems like none of them are able to pull context from what you are doing anymore, and you’ll spend more time fiddling and googling how to make them work than it would take for you to do the task yourself.
In some ways, assistants have gotten worst than almost 10 years ago, despite billions in investments.
As a little bonus, the internet is filled with AI slop that makes finding out real facts, real studies from real people harder than ever.
I write this all mostly to blow off steam, as this stuff has been frustrating me for years now. Let me know what your experience has been like below, I could use some camaraderie.
kick google out your life
Who cares? Stop using Google products. They are an evil company.
I’ve developed a theory. I think the person who put the “don’t be evil” line in the mission statement for Google put it there with a clever reason. Not simply to say to the company “don’t be evil” but so that we the consumers will know that, on the day they remove the line they will have become truly evil and that we should abandon the company and it’s products with all due haste.
Like a canary page
Just so you know, your name’s visible in the “Gemini crashes” image.
Thanks bud
The Assistan/Nest devices have gone to shit as well. When I first bought one about 5 years ago, it could:
- play many games (voice-controlled text adventures, multi-player gameshow-style trivia and party games, etc.);
- play music from my Google Music Library library with no commercials;
- play podcasts from 3rd party podcast providers;
- play almost any radio station that also had livestream feeds
Now all the games are gone, and ‘podcasts’ are just the small subset of podcasters who also upload their episodes to Youtube (whatever feed they used to use had almost every podcaster there was, even obscure ones); asking for specific episodes by episode number or date is totally broken. Playing radio stations is hit or miss, the voice recognition often picks a stream completely unrelated to the one I ask for; it is waaay worse at matching the callsign/city I ask for.
Playing music is intolerable. There’s a stupid commercial for Youtube Music Premium after nearly every track. NO, I will not upgrade to your freaking Youtube Premium.
Enshittification, thy name is Google.
Have you heard of Homeassistant? It’s a self-hosted smart home solution that fills a lot of the gaps left by the most smart home tech. They’ve recently added and refined support for various different voice assistants, some of which run completely on your hardware. I have found they have great community support for this project and you can also buy their hardware if you don’t feel like tinkering on a Raspberry Pi or VM. The best thing (IMHO) about Homeassistant is that it is FOSS.
I got their voice widget, its slow and stupid.
Need to figure out how to connect it to a gpu
NetworkChuck has a video explaining how to configure Home Assistant with voice, using Raspberry Pi and self-hosted LLM.
Voice control of devices you have in home assistant is cool, but I don’t think I would recommend it to an average person who uses Google assistant. Sure it can turn the lights on and off if it’s aware of those entities, but this user is describing playing games, asking for media streams, podcasts, all things home assistant voice does not support (certainly not out of the box).
Fair points! I’ve been tinkering with Homeassistant for a while now. The community has come very far so I’m hopeful that more advanced features will be added as the user base grows.
I have heard of it yeah! Definitely want to try it out… just haven’t gotten around to it yet.
Do you find the voice recognition is decent?
I’m wondering if there’s a paid and private-ish personal assistent. I’m turning away from all the software where I’m the product. Any ideas?
Hmmm I couldn’t really find anything. The only way to guarantee that is to have models that run purely locally, but until very recently that wasn’t feasible.
Smaller AI models that could ruin a phone are now doable, but making them useful requires a lot of dev time and only giant data-guzzling companies have tried so far.
Have you heard of Ollama? It’s an LLM engine that you can run at home. The speed, model size, context length, etc. that you can achieve really depends on your hardware. I’m using a low-mid graphics card and 32GB of RAM and get decent performance. Not lightning quick like ChatGPT but fine for simple tasks.
For most people, use Open Web UI (along with its many extensions) and the LLM API of your choice. There are hundreds to choose from.
You can run an endpoint for it locally if you have a big GPU, but TBH it’s not great you have at least like 10GB of vram, ideally 20GB.
I’ve been doing a 90 day test of perplexity pro and so far it’s my front runner. They recently released an assistant that can launch in place of google assistants, it’s able to use screen context and interact with some apps, you can limit what info they collect, they don’t sell your data, and it connects to multiple models.
I like the fact that it looks like you can turn off how it saves my data. But I’m wondering if there are any Europe-based alternatives.
AI is useless at actually helping with normal tasks.
I feel like we were so close to having Jarvis like assistants. Then every company decided to replace the existing tools with their alpha state AI, and suddenly we’re back to square -1.
Yeah pretty much what it feels like to me, everyone wants to cram AI into everything even though it’s often worse and uses far more resources.
AI tools are great at some things, like I had a spreadsheet of product names and SKUs and we wanted to clean up the names by removing extra spaces, use consistent characters like - for a separator, and that kind of thing, and it was very quick to have an AI tool do that for me.
This is by design. They’re trying to frustrate you, because they’ll then upsell you on the “premium” subscription later on that returns the “old ways,” all while mining your data. And if you continue to use the free stuff, they’ll just mine you harder with AI.
They’re angling for a rent-based economy where they’re the landowners and we’re the sharecroppers paying to use their stuff. The only way out is to de-google and start taking your privacy seriously.
the thing about degoogled Android is SafetyNet Support. So, if you rely on digital banks then it is serious issue.
That’s an optimistic view.
But really, that’s just Google being Google.
Even years before the “AI” hype their Assistant kept suddenly losing features that worked perfectly fine before.Just like Android loses features on every major version, and Maps is a skeleton of its former self.
In a company where nobody is incentivised to maintain anything, cutting features is the easier option.
I think that this is the result of a KPI.
At some point there was a fight inside Google between engineering and marketing about how to proceed with product development. Engineers wanted a better product, marketing wanted more eyeballs.
As a result, search became about “engagement”, or “Moar clicks is betterer”.
Seen in this light, your triggering of the assistant four times increased your use and thus your engagement. An engineer would point out that this is not a valid metric, but Google is now run by the marketing and accounting departments, not by engineers.
Another aspect that I only recently became aware of is that in order to get promoted, you need to make a global impact. This is why shit is changing for no particular reason or benefit and has been for a decade or so.
4 times once every few years is still way lower than using it every few weeks, once, as it works the first time.
I didn’t say that it was a valid KPI 😇
I can’t address most of it, but under gesture navigation there’s an option to swipe from the corner to invoke the assistant. I entirely agree that the power button is for “power”, and I don’t know why you would try to change that.
Not for me. I vaguely remember that being a thing, but it’s not with the other features at least.
Weird.
I used the search function to find it, since it’s kinda tucked away oddly.
It just straight up stopped sending me reminders that I’ve scheduled. Literally the one thing I used it for.
I have no idea about Google, I don’t use it, but Alexa, fuck Alexa is just more and more and more awful. It barely hears you, it does the wrong thing, it seems to just, forget timers. The other day my wife asked “What is the weather on Sunday” and it started rattling off about the weather in San Diego. Like, no, WTF Alexa.
I have had a Google home for years and I wholeheartedly agree. It is like they lobotomized it a couple of years ago?
Commands that it could do when I bought it, to my amazement (wow it can do that‽), is long gone. Now it feels like it struggles even with the most simple commands such as playing news or turning on a light.Wonder what happened.
Idk about anyone else, but my struggles to even just execute the command to shut off a timer/alarm…
Stopping timers has always been like that for me.
Through trial and error I found the most successful command is “ok google shut the fuck up”.
The only 100% effective method I’ve found is pulling the plug.
This is because hardcoded human algorithms are still better in doing stuff on your phone than AI generated actions.
It seems like they didn’t even test the chatbot in a real live scenario, or trained it specifically to be an assistant on a phone.
They should give it options to trigger stuff, like siri with the workflows. And they should take their time and resources training it. They should give app developers a way to give the AI worker some structured data. The AI should be trained to search for correct context using that API and that it plugs the correct data into the correct workflow.
I bet, they just skipped that individual training of gemini to work as phone assistant.
Apple seems to plan exactly that, and that is way it will be released so late VS the other LLM AI phone assistants. I’m looking forward to see if apple manages to achieve their goal with AI (I will not use it, since I will not buy a new phone for that and I don’t use macOS)
I don’t use it often but lately it stopped being able to turn off my flashlight for no reason. Can only turn on. I wonder if it’s just to get people to use Gemini. It’s a shame because I found the normal assistant capable enough for my needs.
They have no incentive to fight the voice assistant war anymore. That decisively ended in the late 2010’s with no winner, because they moved onto the next buzzword technology by then. At this point, GA is just on life support, and will continue being a piece of garbage, as they remove more features from it, under the notion that the userbase is not large enough.
