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

I used AI-powered calorie counting apps, and they were even worse than expected

lifehacker.com

Post reply on HN
Print view View original

211–220 of 302 posts

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#211

Post by jonplackett »

mapt wrote: post #203
jonplackett wrote: post #114

Earlier quoted context omitted.

So here’s why that ain’t true. Yoghurt. You can buy zero fat Greek yogurt that has very low sugar. It’s perfect for losing weight. It’s about 50kcals per 100g. And also super high in protein. Or you can buy yoghurt that is full of sugar and is 100kcals per 100g and has lots of fat and hardly any protein. Even a human expert could not tell the difference without tasting them. This is just one example of many.

I wanted to examine this numerically. * Great Value Original Vanilla Lowfat Yogurt, 32 oz Serving size 3/4 cup (170g) 1.5g fat 26g carbs (21 of which are sugar) 5g protein 130 kcal * Great Value Greek Plain Nonfat Yogurt, 32 oz Tub Serving size 2/3 cup (170g) 7g carbs (7 of which are sugar) 17g protein 100 kcal * Great Value Light Vanilla Nonfat Yogurt, 32 oz Serving size 3/4 cup (170g) 15g carbs (12 of which are sug…

https://www.sainsburys.co.uk/gol-ui/product/fage-total-0-nat...

This is the yoghurt I was talking about. It’s a high quality brand here in the UK

54kal per 100g and 10g protein

3g carbs (zero of which sugar)

Ingredients: Pasteurised Skimmed Milk, Live Active Yoghurt Cultures (L. Bulgaricus, S. Thermophilus, L. Acidophilus, Bifidus, L. Casei)

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#212

Post by nvahalik »

adrian_b wrote: post #86
irrational wrote: post #33

Earlier quoted context omitted.

Does that work for homemade food as well? The vast majority of the food we eat is homemade with recipes that don’t have any sort of nutritional information. I’ve always wished there was a simple way to figure out the calories. Taking a picture would be ideal.

For homemade food it should be easier to make reliable estimates of the calorie content, because you know with certainty all the food ingredients and their amounts. The food ingredients with the highest calorie content, like various kinds of seeds or nuts or flour or meal or oil or fat or sugar or dried fruits or dairy products, come usually with calorie estimates from their vendors. For other ingredients, like vario…

Absolutely.

Weighing everything (rather than using volumetric measures) is generally going to be the BEST way to ensure consistency and accuracy.

What's also important is that, in general, even if you are 20% off on something (e.g. I logged 2200 calories but I actually consumed 2600 calories) AND you are planning to eat at a caloric deficit, this usually will mean that you will still lose weight or body recomp. It'll just take a little more time.

But if you are just not tracking, it's _so easy_ to miscalculate your intake to the point where you think "oh this isn't that bad." However, the truth is you consumed 4200 calories and that's a big surplus.

So I/we tend to find the value partially in "simple tracking" to get you aware of what you are actually consuming and then find that transitioning to specific portions to be helpful for "dialing in" and achieving specific targets/goals.

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#213

Post by homefree »

I suspect none of this stuff will matter in the near term. People will just take ozempic or whatever the best iteration is and be done with it.

I’ve lost substantial weight (75lbs) the hard way multiple times, it’s doable but it sucks. If the drugs make it easy with seemingly no downside then why waste time with this other stuff.

Use the drugs, lose the weight, then when thin add in an exercise regimen if you don’t have one.

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#214

Post by jonplackett »

skohan wrote: post #177
jonplackett wrote: post #174

Earlier quoted context omitted.

Yeah there's like 2 or 3 foods you realise you're eating that totally mess you up. For me it was peanut butter and sausages (not together...). Just so many calories and it's not like I even cared about either that much.

I had the same experience. For me peanut butter and apples were my "healthy snack" and were accounting for a huge amount of calories per week.

I found I developed a new value of food based on its deliciousness per kcal.

Some foods are delicious but too calorific to be considered.

Some taste OK but turn out to be exceptional value!

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#215

Post by sudobash1 »

I expect that plenty of these apps are or will be mining these photos for data about their users. I know the cat is already out of the bag as far as online tracking goes, but until now, tracking every meal & snack someone eats has been impossible (except perhaps for the most consummate doordash user).

And the companies most interested in the data would be the large food corporations who bear a lot of responsibility for getting us into this obesity crisis in the first place.

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#216

Post by hammock »

cainxinth wrote: post #102
dack wrote: post #91

Calorie tracking is also about educating yourself about how many calories certain things are, so you can make better decisions. Like, oil is insanely caloric and can accidentally add hundreds of calories, but it's nearly impossible to eat too many greens. Once you learn this, then the tracking is just to keep you honest - your brain knows what to do but it lies to you when it wants to bend the rules and those little…

You develop a sixth sense for how calorific foods are when you track calories consistently. I kept a meticulous food journal for about six months before I realized I didn’t really need to anymore because I had gotten so good at just estimating my totals. Protip: most people underestimate the calories in alcohol

Extra light beer or shot 100

Light beer or wine 150

Regular beer 200

mixed drink 300

Trashy mixed drink 400

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#217

Post by sumeno »

ffsm8 wrote: post #186
sumeno wrote: post #184

Earlier quoted context omitted.

What about when people give up because you massively underestimate their calories? Or when people develop eating disorders because you massively overestimate their calories? If the goal is to learn then accurate information is important, although I suppose it's harder to get a VC to fund.

What about the people that would have given up on the diet without even trying because they just cba to do it "properly"? Ultimately, there is no silver bullet in nutrition.

There may not be a silver bullet but adding randomly generated numbers is not an improvement

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#218

Post by haliskerbas »

wnorris510 wrote: post #183

Founder of https://snapcalorie.com and ex-Google AI researcher here. The article actually gets our pricing wrong, it's completely free to use SnapCalorie, the $79.99 price is a donation to support our research and help us continue providing the best tools to everyone for free. We've published in top peer reviewed academic conferences and our algorithm (can't say the same for other apps) IS actually more accurate than…

How do you deal with sauces / toppings that can be widely variable in macronutrients?

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#219

Post by hammock »

duskwuff wrote: post #19

Funny, I was just discussing this on HN a few days ago: https://news.ycombinator.com/item?id=44185892 There's a lot of questions about the nutritional content of food which you can't answer just by looking at a photo, like "is that a glass of whole milk or non-fat", or "are those vegetables glossy because they're damp or because they're covered in butter". No amount of AI magic is going to solve that.

Those are easy manual adjustments to make. Far easier than estimating an entire meal

Re: I used AI-powered calorie counting apps, and they were even worse than expected

#220

Post by sethhochberg »

skohan wrote: post #177
jonplackett wrote: post #174

Earlier quoted context omitted.

Yeah there's like 2 or 3 foods you realise you're eating that totally mess you up. For me it was peanut butter and sausages (not together...). Just so many calories and it's not like I even cared about either that much.

I had the same experience. For me peanut butter and apples were my "healthy snack" and were accounting for a huge amount of calories per week.

"Healthy" is a pretty loaded word. In the grand scheme of things apples and peanut butter is indeed a pretty healthy snack: good balance of fiber and protein and carbs and healthy fats, and nothing particularly bad like partially hydrogenated oils if you stick to a decent brand of peanut butter. But its not a particularly low-anything snack, so maybe not an efficient use of calories for someone trying to watch their weight. Nuts in general are a pretty caloric food.

Occasionally (usually as a distraction while trying to make a meal plan for the week) I find myself wondering by what we could do differently with the concept of healthy foods that makes nuances like this easier for people to understand, without getting into fad diet territory. I've never had a brilliant idea here because its fundamentally asking the public to have a nuanced understanding in an industry with tons of historical marketing spin, which is... hard. Really hard. Fad diets and diet plans in general exist because someone telling you exactly what to eat is sometimes more effective than trying to give an understanding about why those choices are made.

The reality is that "healthy" is an individualized goal and different foods are a tool for getting to that destination.

Post reply on HN