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

161–170 of 302 posts

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

#161

Post by XorNot »

coltoneakins wrote: post #106
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…

100% agree it is about re-educating yourself about calories in food. I wasn't happy with my weight but it was never 'obese': I am 5' 8" and weighed 187 lbs. Back in November I started tracking calories in the app Cronometer. I lost 35+ lbs down to 151 lbs as of this morning. Even as a 'relatively healthy' dude, I realized just how bad my perception of calories and macros in food was. So, I totally agree with this.

This was my story too - calorie tracking made me reevaluate my whole diet. Suddenly when I couldn't "just have more" I was getting much more interested in the value of what I was having and the quality improved a lot.

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

#162

Post by taeric »

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

Oddly, I think how you track can matter here. If you do it as a lookup of "I am eating this, and it says it was this many calories" then you are not likely to remember and develop a sense of how many calories things have. However, if you do it as "I am eating this, I think it has X calories, but looking it up I found it was Y" that can help remember.

I can try to find the studies, but basically, "guess and check" is ridiculously powerful in learning. Is part of what makes flash cards so strong. Just "ask and answer", not so much.

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

#163

Post by XorNot »

MangoToupe wrote: post #147
kelstar18 wrote: post #132

Earlier quoted context omitted.

Is it ironic that my AI detector is ringing alarm bells at this comment (both its overall cadence, as well as it’s particularly unnecessary use of an em dash)?

Is the em-dash ever "necessary"? It was beloved by nerds on the internet long before there was any whisper of LLMs on the internet. What do you think chatbots are imitating if not humans who also use it?

It was only ever inserted by word processors for me.

No one typing with a regular keyboard would ever bother, certainly not with the HN input box.

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

#164

Post by devmor »

jonplackett wrote: post #159
devmor wrote: post #141

Earlier quoted context omitted.

Yes, macros were key as I was doing a pretty intensive 4-day HIIT program at the time. I actually aimed strictly for my maintenance calories as I was burning 700-900cal in exercise per workout day. Was very hard work, but rewarding. It took about a year to drop that much weight, normally I think it would take longer but I had a very dedicated group trainer helping me stay on track.

That's cool that it worked with your maintenance calories. was that calculated a maintenance for sedentary lifestyle and the exercise was on top, or did you also eat the exercise calories and still lost weight?

The former - the ultimate goal was to get myself comfortable with eating in a way that would keep me at a stable weight and stick with it. I knew this was going to be the hardest part of the lifestyle change, so I opted for a more difficult up front program to ensure I could focus on that while I lost weight.

I think that's something that a lot of people fail to account for when trying to lose weight that ultimately ruins their goals - you have to build habits to sustain the lifestyle you want. Weight loss surgery, eating at a large deficit or working out hard alone are going to get rid of some weight, but most people will gain all of that back within a year's time.

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

#165

Post by myhf »

kamma4434 wrote: post #58
jonplackett wrote: post #57

I used MyFitnessPal to lose 15kg a few years ago and I have a theory that the act of calorie counting (ie the effort of working it out and labour of putting it into the app) is a key part of why it works. It becomes just slightly more effort to eat something and it makes you stop and think. Making it easier I would expect to make it also easier to eat more.

Attention and focus make it work. You must be ‘in it’ - otherwise it wont work.

Of course it will work. Just tell ChatGPT that it is working and it will agree with you.

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

#166

Post by XorNot »

Qem wrote: post #156

I wonder what are the errors bars for calorie counting, even assuming one measures food intake by weight accurately. Are the reference values in food package labelling any good, or is the variability from one batch to another and variability in absorption from one person to another so large that such calculations become an exercise of garbage-in, garbage-out?

It doesn't matter provided it's not systemic. For anything related to diet, average over time is the much more relevant factor.

For example you could track calories by just tallying your grocery bills if you lived alone.

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

#167

Post by username223 »

Traubenfuchs wrote: post #52
senko wrote: post #48

CalAI is just objectively a bad app even discounting its AI calorie estimator as an irrelevant gimmick: * the UX is bad * the stats are laughable * charts worse than nothing (really, misleading to look at) * lacking basic functionality such as “duplicate for today” * can’t see or export the meal photo * their “streak” attempt at gamification is so bad it literally cannot count And yes, the AI there is atrociously bad…

We live in a post quality age. Consumers just don't care. AI dialed this to the max: The early vibe coding startup catches the worm. Working with designers, doing A/B tests, QA, product management, nowadays all of this will make you lose to the competition. You just need to get something out that looks as if it works, that makes users feel as if it works, whether it really does or not, whether the quality is atrociou…

It's not that consumers don't care -- it's that "they" (i.e. "we") have been beaten down.

Connect an image labeling API to the USDA's database of nutrients, make a slick-looking app, and you have a product. Pay for some marketing, offer a three-day trial after which you auto-bill for a year, make refunds as difficult as possible, and you have a business. At $30/yr, 10k subscriptions (deliberate or accidental) gets you $210k after app store commission. If you're lucky, you get bought out for even more. If not, you still made good money for not much work.

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

#168

Post by hn8726 »

kelstar18 wrote: post #132
vjulian wrote: post #105

I use ChatGPT (4o model) to track my daily macros, specifically calories, protein, fat, and carbs. I have a prompt containing my macro targets and a list of the foods I typically eat or have at home. Throughout the day, I report my meals, for example five large eggs, two slices of sprouted wheat toast, and a cup of spinach with a pat of butter. It calculates the macros for each meal and keeps a running macros total s…

Is it ironic that my AI detector is ringing alarm bells at this comment (both its overall cadence, as well as it’s particularly unnecessary use of an em dash)?

why are people insisting that an em-dash is exclusive to llms somehow, when on a mac it's super easy to type dash, en-dash and em-dash — just type dash, option + dash or shift + option + dash. I got used to defaulting to em-dash (even if incorrectly) and now I'll be categorized as an llm for that?

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

#169

Post by fwip »

mapt wrote: post #95
jonplackett wrote: post #55

I always just assumed these were terrible. There just isn’t enough info in a photo, even for the world’s leading calorie counting expert, to give a sensible estimate of the calories content. Ans even more so for macros. Add to that the fact vision is still pretty crap and you have a complete joke that I can’t believe anyone is paying for.

However bad these algorithms are (and we're talking very wide intervals in multiple dimensions of uncertainty), you could immediately improve the vision/volume calculation part with a modest change - like requiring a size reference. "Place a unit of currency next to the plate, then take at least two photos of the plate from different angles" can get you pretty close to an accurate volume. If they aren't doing even th…

The article says that at least the first app trialed does recommend putting a size reference in.

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

#170

Post by kelipso »

mock-possum wrote: post #140
yreg wrote: post #107

Earlier quoted context omitted.

> most people underestimate the calories in alcohol Funny, I feel the other way around. I kept hearing about how much calories there are in alcohol, and then when I started calorie counting I didn't find it so high. Like 6 shots of gin are ~550kcal and enough to get anyone pretty drunk. Unless one is a regular heavy drinker it's not that hard to once in a while budget calories during the day to be able to get a few s…

Sure, that means that 6 shots of gin basically replaces one whole meal.

If 550kcal is one whole meal to you, then 6 shots of gin will get you absolutely blasted, probably black out too.
Post reply on HN