Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

He asked AI to count carbs 27000 times. It couldn't give the same answer twice

diabettech.com

Post reply on HN
Print view View original

101–110 of 329 posts

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#101

Post by 2ndorderthought »

jaccola wrote: post #65
engineer_22 wrote: post #39

Earlier quoted context omitted.

I am asking a lot here, but school needs to be training people what AI is and what it's weaknesses are and how to use it... My school taught me to use a calculator. It also taught me how to check my work when I relied on the calculator. AI is a very complicated calculator - you give it an input, magic happens, it gives you an output. Really no different, to a layman.

To be fair, this should probably be covered by basic physics/maybe cooking classes. “You can’t determine the calories in food by looking at it” isn’t really ML specific.

Won't help much if kids are ai'ing their way through physics then ten years later need to go on a diet having not applied the knowledge possibly ever or exercised their critical thinking skills

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#102

Post by tcoff91 »

nextlevelwizard wrote: post #71
edu wrote: post #59

Earlier quoted context omitted.

Curious, why it was easier to use an LLM vs a non-AI app with a DB of foods? Seems that in this case a traditional approach would be more precise and more environmentally efficient to get to the same results.

Any app I have used before has asked me to look up the foods and add them manually and usually there has been ads or subscriptions involved. Much easier for me to take pictures of the packets while making the food, the weight the final bulk product and then when I eat just weight the plate and say “500g of casserole” and the LLM spits out the calories and keeps track of the daily consumption

Are you giving the LLM the weights of the ingredients as you go? Sounds like a great system.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#103

Post by snapcaster »

throwaw12 wrote: post #92
endymion-light wrote: post #43

There's an incredibly serious lack of education with how LLMs & carb-counting works. This entire article would be better suited to astrology.com than hackernews. When I opened it up, I assumed the author would have at least attempted a calculation service, maybe even placed something like the size of the meal into an actual model, using the integration of pre-existing tools that are (slightly more) accurate. Hell - m…

I feel like you didn't understand the goal of this study > The DTN-UK stated earlier this year that generic LLMs must never be used as autonomous advisory calculators for insulin delivery. This data is the quantitative evidence base for that statement. This study is to prove that you should not rely on LLMs

But it's stupid. If i smack myself in the head with a hammer is that proof hammers shouldn't be relied on?

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#104

Post by monegator »

embedding-shape wrote: post #80

> You’d expect the same answer each time. It’s the same photo, the same model, the same question. But you won’t get the same answer. Not even close — and the differences are large enough to cause a hypoglycaemic emergency. Already the first paragraph highlights the issue; unless you set temperature=0.0 and the model can actually do reproducible inference, none of the "answers" you get are deterministic! But it's a ve…

This is one of the reasons i never used LLMs for anything related to coding. And i never intend to do. If i tell the thing to generate, will it generate the same thing, every time? will it change stuff that is working because the random number generator will conjure a slightly different answer?

i'd be ok with it if i was generating a picture of X, or some word salad about Y, but not for code. Never for code.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#105

Post by fcarraldo »

renticulous wrote: post #86
2ndorderthought wrote: post #28

Earlier quoted context omitted.

The average person has no idea this is true. And the average person cannot tell when this is the case. So we have a bunch of people, going their way through school, and then when they get stuck relying on AI. The future is gonna be wild.

Here's technical literacy of population on display. I love these prank examples which show the true education of populace. https://www.youtube.com/shorts/B7c9qJcRnVk

True education? What idiot would say yes to this?

Even if you _know_ the debit card transaction is safe, there’s no reason to risk it when a weirdo is filming you with some wild contraption.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#106

Post by fabian2k »

throwaw12 wrote: post #92
endymion-light wrote: post #43

There's an incredibly serious lack of education with how LLMs & carb-counting works. This entire article would be better suited to astrology.com than hackernews. When I opened it up, I assumed the author would have at least attempted a calculation service, maybe even placed something like the size of the meal into an actual model, using the integration of pre-existing tools that are (slightly more) accurate. Hell - m…

I feel like you didn't understand the goal of this study > The DTN-UK stated earlier this year that generic LLMs must never be used as autonomous advisory calculators for insulin delivery. This data is the quantitative evidence base for that statement. This study is to prove that you should not rely on LLMs

The paper itself is a lot clearer about the purpose. The blog post reads very clickbaity and doesn't really explain the context well.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#107

Post by tcoff91 »

edu wrote: post #66
mottiden wrote: post #45

I am surprised that people believe that calories can be counted correctly from a single photo

Issue is there are many apps claiming they can do that, and for many people are “magic”. We should not allow companies to lie blatantly to the customers. Edit: r/blame/lie/

These calorie counting picture apps should be sued for false advertising.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#108

Post by lordgrenville »

vector_spaces wrote: post #37
PUSH_AX wrote: post #15

Earlier quoted context omitted.

It’s worse, I bet there are apps in the App Store that do this, the users just have no idea on the accuracy

There is a very popular app for macro counting called Cal AI that was reported to have been written by a high school student with over $1M in revenue. Looks like it was just acquired by MyFitnessPal

Wow, yeah. "The result is an app that the creators say is 90% accurate".

https://techcrunch.com/2025/03/16/photo-calorie-app-cal-ai-d...

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#109

Post by pjc50 »

vidarh wrote: post #61
throwaway260124 wrote: post #25

Earlier quoted context omitted.

But nothing prevents llms from being RLed to do this right? But does training llms to be better at this, improves their world model or does it only make changes at the surface?

Yes, something prevents llms from being RLed to do this: You can't see through something opaque to determine whether there's something high calorie or low calorie out of sight. The problem itself is unsolvable given the data provided. You could conceivable make it better at making guesses, but they will inherently always be guesses that will sometimes be wildly off.

> You can't see through something opaque to determine whether there's something high calorie or low calorie out of sight

https://www-users.york.ac.uk/~ss44/joke/3.htm "There is at least one field, containing at least one sheep, of which at least one side is black."

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#110

Post by zipy124 »

endymion-light wrote: post #43

There's an incredibly serious lack of education with how LLMs & carb-counting works. This entire article would be better suited to astrology.com than hackernews. When I opened it up, I assumed the author would have at least attempted a calculation service, maybe even placed something like the size of the meal into an actual model, using the integration of pre-existing tools that are (slightly more) accurate. Hell - m…

Honestly it's scary how misunderstood this is by the general public, the media and EVEN scientists.

There is a shocking amount of Computer Vision tasks where the scientists claim you can get X info from a picture of Y and it's like, even with ML/AI you can't extract data where there isn't any. The fact I can add an arbritrary amount of high-calorie fat to a meal without changing the appearance by defintion shows it's pointless. A 1000 calorie and 100 calorie milkshake can look identical, and you'd have no way of working that out via an image even if it was a super-intelligent system.

Similarly I see it in things like extracting material of an object from an image of it in serious research papers, which for the same reason cannot be done, since how an object looks has very little to do with what its made of, else painting and other art would clearly be impossible. The information is just not there within the data.

Post reply on HN