It’s not exactly an ai-task, I guess? Like pretty much the only ai-related thing there is to classify stuff in ocr-ed receipts (technically, one can opencv whatever is in the fridge, but I suspect it won’t be reliable enough).
Bruh. If AI is being taught to drive cars on the open road then I feel like cameras to detect what’s in your fridge is pathetically easy in comparison and very much an AI task
That’s how you get weird things like the AI determining that your favorite items are jam, baking soda and whatever you left at the back of your fridge to rot for six months.
It is easy to detect what’s in your fridge. We have that today on some smart fridges.
The problem to be solved though is
what’s in your fridge
what’s not in your fridge
what do you consume vs throw away
what do you buy
where do you shop
what prices are available
what’s the best way to minimize cost and store trips
what’s your metric for how to balance that
Of those things, AI is really only helpful for determining the metric for how much money you need to save to add another grocery stop, and knowing that the orange blob is probably baking soda.
Most of the rest of that is manual inputs or relatively basic but tedious programming, and those are the parts that would be the most annoying.
I say this as a person who has repeatedly utterly failed to use https://grocy.info/ because actually recording what you eat vs throw away is painful.
This isn’t a great AI problem not because AI can’t help, but because the tedious part isn’t the part it can help with right now.
Yeah its not even remotely possible for someone to manually input that they eat 2 slices of cheese and 20grams of butter and 20 grams of jam every time they do so. And it is not feasible for AI to see inside closed packages or jars how much is eaten.
Yeah, kinda. Except you’ll likely need a camera or two for each shelf of the fridge (given the layout remains unchanged), and also you have to make sure they don’t get covered with ice/spilled milk/whatever or blocked by a box of some stuff. Aaaalternatively, you install a receipt scanner and touch scrreen which asks you what you took and updates an internal db accordingly.
No, not even kinda. Fully. Amazon has stores you can walk in and take whatever you want off the shelf and leave. If you put it back somewhere else, even if not on the same shelf, it can still track that.
I actually work in this field and it’s a lot more complicated than it sounds. When you’re training AI to recognize products in a store, you have a set list of products it needs to be trained on. A person might go to many different stores which increases the possible variation of products exponentially. Amazon’s model is also much more complex than just cameras, involving weight sensors in shelving, pressure detection, facial recognition. A store where everything is laid out in predictable, well lit, organized rows is already a nightmare. A fridge, even if it’s way smaller, is way, way less predictable
A typical Amazon store that I’ve been to is around 12,000—16,000 feet. A refrigerator is approx 20-25 cubic feet of real estate.
Miniaturization of any system is always going to be a massive hurdle.
Amazon uses biometric recognition to determine if a person has picked up something, RFID tags, Weight Sensors, cameras, Laser gates and probably some other things they aren’t telling us about.
They also know a specific list of the items in the store and have 3d models for where each item is. nothing unexpected.
For the fridge to work it would need to know every product ever made and have accurate and reliable scans of the existing product. Sure it might be able to find SOME of the same type of item but it will only work once it can find the EXACT item that I want everytime.
Good luck finding my favorite brand of Guachujung that can’t be purchased online and is only available from a shady mom and pop grocery in Asia town.
then I feel like cameras to detect what’s in your fridge is pathetically easy in comparison
But you’re skipping over a huge amount of context that’s missing. It’s context we (as humans) take for granted. What’s the difference between a jar and a bottle? Is the cream cheese in a tub or in a little cardboard container? Then it would need to be able to see all items in a fridge, know the expiration dates for each thing, know what you want to get, how quickly something gets used, etc.
Some of those things are more straightforward, and some of them need data well beyond “this container has milk”. The issue isn’t processing all the data, but acquiring it consistently and reliably. We humans are very chaotic with how we do stuff in the physical world. Even the most organized person would throw off an AI system every so often. It’s the reason self driving cars are not a reality yet and won’t be for a while.
The problem is that “AI” is a completely ill-defined term. The commenter above used the definition of it just being a more complex program and then they argued that you don’t need a more complex program. That’s as good of a definition as any other.
By “ai tasks” I mean smth where ai is actually useful, such as object/pattern recognition, object classification, making predictions based on past data, etc. Can one train an ai to predict they need to buy onions when they have less than X in their fridge? Yap. Can one do the same with an if statement and prevent themselves from running into issues when ambient temperature on Mars rises? Also, yes.
An AI task would be literally anything impossible or slow for a human to do that a computer could do instead (without having developers specifically work for months to provide explicit instructions on how to do it). Kinda weird to see technology evolving like this and still set arbitrary defining parameters like that
I mean, think of it like physical tools. You can use a screwdriver like a hammer, but it’s slow, not what it was designed for, has a higher chance of injury, etc. but if it’s something better done with a hammer, well… That’s a hammer task, not a screwdriver.
“AI tasks” would then be things that aren’t as easily solved with other tools. You run into a lot of issues with the refrigerator and AI. You can’t easily just visually verify what things are. What if you don’t have a standard package, and are using, say Tupperware. Or you have a jar with some milk and a jar with some cream. Those aren’t as simple as just having a camera look at it and figuring it out.
In this case, a more simple, manually (either typed or scanned if packaging allows) managed DB would be much better for the refrigerator itemization. Then, for the “finding best prices” problem, there already exist some apps that do that, but I could see having an AI implemented just in this step to potentially be beneficial depending on how you’re finding sale info.
Hmm, guess I wasn’t clear. It’s not “arbitrary defining parameters”, but more of “ai is a tool that better solves specific types of tasks” kind of thing. Can you replace an if statement with an ai? Yes, but that’s somewhat like hammering a screw (that is to say, inefficient).
Why are so many of you trivializing the fact that providing perfectly formatted input data that having set logic figure something out is a VERY different thing than providing a firehose of data and then asking the software to make sense of it? Like have you been paying attention here at all?
In this case I would suppose that there’s no need to get firehose of data, especially if run locally. The user only has so many shops around and the fridge is not a factory scale big
Yeah true. I guess I should have said a mish mash of data. It’s more about the fact that the data wouldn’t necessarily be in some regular format – the majority of the work you want the machine to do is find and compile that data
In my experience, most things touted as AI are mostly rule-based or graph-based, with a sprinkling of some classification somewhere for a manager to get that sweet VC money.
That’s not to say that this couldn’t be done with AI, particularly one that is trained on top of a rule-based system to find the best options for given circumstances.
It’s not exactly an ai-task, I guess? Like pretty much the only ai-related thing there is to classify stuff in ocr-ed receipts (technically, one can opencv whatever is in the fridge, but I suspect it won’t be reliable enough).
Bruh. If AI is being taught to drive cars on the open road then I feel like cameras to detect what’s in your fridge is pathetically easy in comparison and very much an AI task
That’s how you get weird things like the AI determining that your favorite items are jam, baking soda and whatever you left at the back of your fridge to rot for six months.
It is easy to detect what’s in your fridge. We have that today on some smart fridges.
The problem to be solved though is
Of those things, AI is really only helpful for determining the metric for how much money you need to save to add another grocery stop, and knowing that the orange blob is probably baking soda.
Most of the rest of that is manual inputs or relatively basic but tedious programming, and those are the parts that would be the most annoying.
I say this as a person who has repeatedly utterly failed to use https://grocy.info/ because actually recording what you eat vs throw away is painful.
This isn’t a great AI problem not because AI can’t help, but because the tedious part isn’t the part it can help with right now.
Yeah its not even remotely possible for someone to manually input that they eat 2 slices of cheese and 20grams of butter and 20 grams of jam every time they do so. And it is not feasible for AI to see inside closed packages or jars how much is eaten.
Probably would make sense to start with the receipts for what you purchase and aggregate lists from there (pantry, freezer, fridge, etc.).
Yeah, kinda. Except you’ll likely need a camera or two for each shelf of the fridge (given the layout remains unchanged), and also you have to make sure they don’t get covered with ice/spilled milk/whatever or blocked by a box of some stuff. Aaaalternatively, you install a receipt scanner and touch scrreen which asks you what you took and updates an internal db accordingly.
No, not even kinda. Fully. Amazon has stores you can walk in and take whatever you want off the shelf and leave. If you put it back somewhere else, even if not on the same shelf, it can still track that.
A fridge is a joke.
I actually work in this field and it’s a lot more complicated than it sounds. When you’re training AI to recognize products in a store, you have a set list of products it needs to be trained on. A person might go to many different stores which increases the possible variation of products exponentially. Amazon’s model is also much more complex than just cameras, involving weight sensors in shelving, pressure detection, facial recognition. A store where everything is laid out in predictable, well lit, organized rows is already a nightmare. A fridge, even if it’s way smaller, is way, way less predictable
A typical Amazon store that I’ve been to is around 12,000—16,000 feet. A refrigerator is approx 20-25 cubic feet of real estate.
Miniaturization of any system is always going to be a massive hurdle.
Amazon uses biometric recognition to determine if a person has picked up something, RFID tags, Weight Sensors, cameras, Laser gates and probably some other things they aren’t telling us about.
They also know a specific list of the items in the store and have 3d models for where each item is. nothing unexpected.
For the fridge to work it would need to know every product ever made and have accurate and reliable scans of the existing product. Sure it might be able to find SOME of the same type of item but it will only work once it can find the EXACT item that I want everytime.
Good luck finding my favorite brand of Guachujung that can’t be purchased online and is only available from a shady mom and pop grocery in Asia town.
LASTLY… what’s a camera going to do with this:
Nah you will just get 45 additional fridges and you will have predefined places for all the products. Then the “AI” will work
Well, obviously that’s one package of Tillamook ice cream, what’s the problem?
Given you re-design it from the ground up, that’ll work 🤷
Good luck guessing how much milk is still left in the non transparent package
But you’re skipping over a huge amount of context that’s missing. It’s context we (as humans) take for granted. What’s the difference between a jar and a bottle? Is the cream cheese in a tub or in a little cardboard container? Then it would need to be able to see all items in a fridge, know the expiration dates for each thing, know what you want to get, how quickly something gets used, etc.
Some of those things are more straightforward, and some of them need data well beyond “this container has milk”. The issue isn’t processing all the data, but acquiring it consistently and reliably. We humans are very chaotic with how we do stuff in the physical world. Even the most organized person would throw off an AI system every so often. It’s the reason self driving cars are not a reality yet and won’t be for a while.
What is an “ai task”? Their task is anything we assign them to do.
The problem is that “AI” is a completely ill-defined term. The commenter above used the definition of it just being a more complex program and then they argued that you don’t need a more complex program. That’s as good of a definition as any other.
By “ai tasks” I mean smth where ai is actually useful, such as object/pattern recognition, object classification, making predictions based on past data, etc. Can one train an ai to predict they need to buy onions when they have less than X in their fridge? Yap. Can one do the same with an if statement and prevent themselves from running into issues when ambient temperature on Mars rises? Also, yes.
An AI task would be literally anything impossible or slow for a human to do that a computer could do instead (without having developers specifically work for months to provide explicit instructions on how to do it). Kinda weird to see technology evolving like this and still set arbitrary defining parameters like that
I mean, think of it like physical tools. You can use a screwdriver like a hammer, but it’s slow, not what it was designed for, has a higher chance of injury, etc. but if it’s something better done with a hammer, well… That’s a hammer task, not a screwdriver.
“AI tasks” would then be things that aren’t as easily solved with other tools. You run into a lot of issues with the refrigerator and AI. You can’t easily just visually verify what things are. What if you don’t have a standard package, and are using, say Tupperware. Or you have a jar with some milk and a jar with some cream. Those aren’t as simple as just having a camera look at it and figuring it out.
In this case, a more simple, manually (either typed or scanned if packaging allows) managed DB would be much better for the refrigerator itemization. Then, for the “finding best prices” problem, there already exist some apps that do that, but I could see having an AI implemented just in this step to potentially be beneficial depending on how you’re finding sale info.
Hmm, guess I wasn’t clear. It’s not “arbitrary defining parameters”, but more of “ai is a tool that better solves specific types of tasks” kind of thing. Can you replace an if statement with an ai? Yes, but that’s somewhat like hammering a screw (that is to say, inefficient).
AI is just a program that learns from the information you provide it to predict the next element in a series.
If you want a program to check whats in your fridge, a simple spreadsheet updated whenever you empty a bag is just as good.
An use for AI could be to update the spreadsheet with images from the inside of the fridge but you would need cameras that can work inside fridges.
so it is an ai task, but requires some setup
With that attitude, everything is an ai task but its like using a sledgehammer to crack a nut
Why are so many of you trivializing the fact that providing perfectly formatted input data that having set logic figure something out is a VERY different thing than providing a firehose of data and then asking the software to make sense of it? Like have you been paying attention here at all?
In this case I would suppose that there’s no need to get firehose of data, especially if run locally. The user only has so many shops around and the fridge is not a factory scale big
Yeah true. I guess I should have said a mish mash of data. It’s more about the fact that the data wouldn’t necessarily be in some regular format – the majority of the work you want the machine to do is find and compile that data
Agreed, data regularisation will likely be a pain for this task
AI could potentially do, “write me a python script that scrapes a website for grocery prices and compares them with another” or something.
In my experience, most things touted as AI are mostly rule-based or graph-based, with a sprinkling of some classification somewhere for a manager to get that sweet VC money.
That’s not to say that this couldn’t be done with AI, particularly one that is trained on top of a rule-based system to find the best options for given circumstances.