Anyone who has participated in calorie-tracking for an extended period of time can tell you that the visual appearance of food can be highly misleading to the number of calories in it.
I'm all for making it easier for people to lose weight but this app may honestly have the reverse effect. If the app estimates calories too low (and therefore the individual eats more), many people will get frustrated with the lack of progress and give up. If the app estimates too high, the individual will lose weight, but diet fatigue and other negative side effects of being at a >500 calorie deficit may make the diet too difficult to maintain.
I actually went over this recently with someone who wanted to build something similar. The conclusion was this is a very difficult problem to solve, probably intractable to some extent. You can't see the complete composition of the food with a standard camera. E.g. I make a salad which is maybe 300 calories. Then I sprinkle some croutons and bacon on top, which will mostly be in the middle. Then I put dressing on it, which is hard to estimate. That dressing hides the bacon and croutons and, since it contains a lot of oil, could seriously skew the measurement one way or the other. Now I mix it all around and the AI can't tell how much dressing was used at all.
I pick this example because I've seen specifically this cause problems for people trying to lose weight. They think their eating a salad, not realizing they've thrown an extra 500 calories on top.
Another case: I sit down to breakfast, having made myself eggs and toast. One of if not the largest contributor to my calorie intake will be the amount of butter on my toast. If I use four pats that will probably exceed my calorie intake from eggs. If I use one, not as much. I sincerely doubt it's realistic to tell the difference with any sort of precision.
I think even if you have volume factored in like photogrammetry/lidar, the inside of the food could be something else too like a chunk of meat inside potatoes
Steelmanning this: You take your phone out and snap a picture and it gets added to a running total without typing into a tiny keyboard or doing any math. You consult your total next time you're thinking of eating.
Critiquing: You still need to figure out serving sizes - it's going to need to ask how many servings. Nutrition labels also aren't available for any number of things.
Anecdote of one... about 8 years ago I put a lot of effort into losing weight... when I was eatng a 1500 calorie/day diet, I wasn't losing weight... per a nutritionist friend who looked at what I was eating suggested closer to 2800 (6'1" tall, 370# at the time) and when I did, I started losing weight. Note this was combined with crossfit 3-4 days a week both on the lower and higher calorie intake.
If you have a really dysregulated metabolism, your body can definitely work against you when consuming too little.
Had a friend who came to me with the same idea. In challenge of the idea I sent a picture of some chopped cucumbers and tomatoes, and an other picture with the same chopped vegetables drizzled with a copious amount of olive oil. I asked if they can tell which one is which. The difference was hundreds of calories and you could not tell which one is which (least of all how much oil there is on the one with the oil.)
That of course feels like a "weird" edge case, but it illustrates the general problem that butter/oil/sugars can pack a lot of calories and have no or almost no visual signature.
You're right, but I think the general public is largely ignorant about calories and nutrition. Even basics like 4 cals per gram of protein and carbohydrate, 7 for alcohol, 9 for fats. Or even what a carbohydrate really is versus a "sugar", which people talk about as bad.
There's a sweet spot for an app that is inaccurate with a market that wants it but doesn't understand how inaccurate it is.
Kind of like how I could vibe code an app, get it to "work", think it's great and be ignorant of the many ways it will break or isn't working that a knowledgeable developer could.
The general public's understanding of food is still stuck in 1990s "destroy all fats (and completely ignore the sugar we replaced it with)" diet culture.
The fact that people still believe in reducing fat as it's own goal (instead of being an easy way to reduce calorie content) is a testament to how bad the public is at identifying fact from fiction.
Then you have shit like the influencer foods, "Feastables" and "Hydration beverage" Prime, which is just flat soda. It's pathetic.
Or think of all the dude bros who insist on dry scooping cup fulls of protein+caffeine powder, and going home to gorge themselves on two pounds of chicken breast, and yet doing absurdly normal amounts of weightlifting or exercise that requires no modifications to their already protein overloaded American diet.
Diet culture is what is fucking American health. People read fucking tabloids that bad-faith regurgitate poorly done "science", funded by the council for selling more food, and insist that since "Woman's Health" says that scientists say chocolate both kills and saves you, scientists are dumb and know nothing, even though THE ACTUAL SCIENCE NEVER CONCLUDED ANYTHING, because the scientific paper was just an observational study!
Related is the fear some have of Saturated Fats and Meat. So many people don't even realize that the body does need some Saturated Fats, or that fats are often a mix of them and vary by the species, breed and how they're fed.
It doesn't help in how far some foods have been bred in the past century and a half in particular. Or how different people with different genetics may react to certain foods.
Everyone keeps using this example, but you have the exact same problem calorie counting any food that might be lathered in fat. It's why people underestimate their calorie intake by 30%+.
You could level the same criticism at Cronometer and MacroFactor when you try to log food you received at a restaurant. Yet those apps are still useful (and I think requisite) for knowing what you're eating. And you should probably 1.5x the calorie estimation when you eat out.
What's interesting is whether this app can accurately estimate food at all. If it can, then that's a huge win and you can add your own buffer zone for oils like you already have to do when you count calories. ...Or chill on the butter and restaurant food when you're supposedly trying to lose weight.
> Everyone keeps using this example, but you have the exact same problem calorie counting any food that might be lathered in fat.
Not really. In practice you need to know the ingredients to estimate the caloric value. Either because you prepared the meal, or because someone who wrote the recipe of it calculated and wrote it on the packaging/menu.
> If it can, then that's a huge win
But that's the point of the example. That it can't. If it could, that would be good. But it can't do it, and not because the app is deficient in some way, but because the necessary information is not available in the image.
> Or chill on the butter and restaurant food when you're supposedly trying to lose weight.
Yes of course. And that is one of the things you learn when you do calorie counting. The practice drives home that message, and many others. But you are not going to learn that if the app hides the signal from you.
The 1st issue I'd think of would be scale.. eg. identical looking plate of food in EU vs USA. The images might look identical but the USA one would be scaled up and contain much more calories.
Everything that could be in the image for scale reference would also be scaled up along with the food.
Many people will analyze this from a tech perspective. I urge you not to. This isn't about whether the technology is good or bad. The real reason they succeeded is their mastery of marketing, particularly TikTok and influencer marketing. Understanding distribution is far more important than knowing how to build something, and this is truer now than ever before. I know it stings but its the truth.
I didn't analyze this for either: rahter what is what is the typical outcome for young humans who achieve a high degree of success/fame before their prefrontal cortex is fully formed.
As we understand more about brain development in kids, I think and under studied aspect are kids who got access to a lot more money than normal typical kids have, and the results such wealth brings.
> I think and under studied aspect are kids who got access to a lot more money than normal typical kids have, and the results such wealth brings.
As opposed to the kids born on planets without atmospheric oxygen, of course. Those kids don't stand a chance.
There's always some advantage others have. Money, good looks, distribution, connections, right place right time.
"Wealth inequality" isn't going to disappear overnight, and lamenting about it won't get us closer to success.
We're all dropped into the Darwinian gradient landscape. Some of us have better starting positions. While we sit and wait for policy decisions to make things easier, our job remains to find gradients that aren't too steep, aren't over-explored by the masses, and that give us some modicum of joy to spend our lives upon.
The minnows and gazelles have it much worse than us. Praying mantises, anglerfish, and the hosts for the parasitoid wasps are practically living in a daily Kafkaesque horror. Meanwhile we're in our own dopamine drip Disneyland with near-infinite degrees of freedom and plenty of years on the clock (for most of us).
I think you missed the part about "[achieving] a high degree of success", in particular the achievement. They are referring to young people who make a successful business rather than those who are born to parents who made a successful business.
The point of looking at this from a technical perspective though is that the underlying tech doesn't actually work, and it's just a smoke and mirrors game built on marketing.
Like Theranos. And Nikola. And Fyre Festival. Etc.
Age is irrelevant, unless we're trying to tell youngsters that fraud is an acceptable means to get ahead in life. But then again given our current political environment maybe that is what we're trying to tell the next generation.
EDIT: the app now also just reads nutrition labels as a backstop. Nutrition labels already include the calorie data, so the app isn't doing anything there.
> But then again given our current political environment maybe that is what we're trying to tell the next generation.
There's no trying.
The US has played "Just grift your way to money" as a standard means of operating since at least the dotcom boom. A reason so many young and poorly educated people jump at obvious MLM type scams and other scams is because they feel that everything is a scam, so surely they can get in on it too, right?
And everything IS a scam. Coke doubled in price in the past 5 years. I promise you their costs did not double. Their costs are Labor (highly automated), water (they almost always have sweetheart deals for dirt cheap water, cheaper than you pay), and one of the most subsidized commodities available, HFCS, or alternatively, a sprinkle of dirt cheap chemicals for their diet sodas.
People feel that, even when they don't understand or even recognize it.
People recognize that the US has been a scammy free for all for decades now. Everyone for themselves, fuck you, got mine.
We are on like the third generation raised this way. The people who took "Greed is good" to heart had kids, and raised them with it as a core principle.
Jordan Belfort, the guy who Wolf Of Wall Street is based on and spent time in prison for scamming his clients in basically the same way modern crypto pump and dumps work, now sells out auditoriums as a motivational speaker for fucks sake.
My reasoning for evaluating the relevancy of this app:
1. If the food being scanned has a nutrition label, I don't need this app.
2. If there's no nutrition label, the app can't possibly extrapolate the nutritional information. It can't estimate portion size or the ingredients in the recipe.
3. If the app can't extrapolate nutritional information, I don't need this app.
I think the key insight here is that actually counting calories is not needed by the app's demographic. Possibly just getting them to pay attention to what they are eating is enough for them to see progress or at least feel like they are doing something.
Recently I have started running dish descriptions through deepseek-r1:8b to give a rough estimate on calories and it is sufficient, at least for my cooking. Of course this will hallucinate on complex cases, and arguably simple dishes are easy to count. Still, counting by hand is tedious compared.
I am happy with a rough number on a dish, I do not need precision to know if I am not eating enough calories. Note there are errors on the result and reasoning, but still this dish should be around the ballpark of 500 cal. I figure running this through a larger model might be more accurate. I wondered if maybe I wanted to create an app for that, but I am happy not to.
Yes, simple descriptions could be parsed with NLP, and yes, calories could be inferred with a database.
>>> Calorie count of a dish that has: rice, broccoli, two pieces of turkey, and a fri
... ed egg. Assume this is a normal portion, for instance, there are 80g of rice.. Re
... turn the result in a json structure
<think>
Alright, so I need to figure out the calorie count for a dish that includes
rice, broccoli, two pieces of turkey, and a fried egg. The user mentioned it's
a normal portion, like 80g of rice. Hmm, okay, let me break this down step by
step.
First, I should find out how many calories are in each ingredient separately.
Let's start with the rice. Rice is a common staple, so I think 80g of cooked
rice has about 130 calories. I've seen that number before, but I should
double-check to make sure it's accurate.
Next up is broccoli. Broccoli is pretty low in calories, right? A portion of
around 100g should be about 25-30 calories. Wait, maybe a bit more if it's raw
or cooked differently, but I think for this purpose, 35 calories is reasonable.
Then there are two pieces of turkey. Turkey can vary based on the cut and
whether it's cooked. Let's assume these are regular chicken breast slices, each
around 50g. Each slice would have about 110 calories, so two pieces would be
around 220 calories. But I should make sure that I'm not confusing turkey with
another type of meat. Turkey does tend to be a bit higher in calories than
chicken sometimes, but 110 per slice seems right.
Lastly, the fried egg. A single fried egg is usually about 140-150 calories
depending on how it's made. Since there's just one egg, that's around 140
calories. I think that's correct because yolks add a good number of calories
due to fat content.
Now, adding all these up: rice (130) + broccoli (35) + turkey (220) + egg
(140). Let me sum them: 130 plus 35 is 165, plus 220 makes 385, and then plus
140 gives 525. So the total would be around 525 calories.
Wait a second, maybe I should consider if there are any other ingredients or
whether portions were different. For instance, sometimes turkey portions can be
larger or smaller depending on the meal. But since it's specified as two
pieces, each at about 50g, that seems okay.
Also, considering preparation methods: fried egg might have more calories if
it's done in a certain way, but I think one fried egg is standard. Broccoli's
calorie count could vary slightly, but for simplicity, the 35 seems fine.
Is there any chance I'm missing something? Maybe adding spices or sauces, but
unless specified, I shouldn't assume that. So the total should be around 525
calories in a normal portion as described.
</think>
```json
{
"calories": {
"rice": 130,
"broccoli": 35,
"turkey": 220,
"fried egg": 140,
"total": 525
}
}
```
This is completely wrong. For example, you can increase the amount of oil or butter in a recipe, doubling or tripling its calorie count, and you would never be able to tell from a picture.
The point of the app is to figure out the calories of a meal automatically by taking a photo.
Without knowing the amount of sugar, butter, oil, etc. is used in a dish, one cannot know if a dish is worth 250 kilocalories or 750 kilocalories.
If I need to manually fill in details of ingredients and amounts to get to the calories to be have an error margin of less than 100%, then the app is not useful and is at best misleading.
Most restaurants smuggle obscene amounts of butter and sugar into dishes to make them more delicious so you'll come back. It's not unreasonable to assume that every subcomponent of a recipe might have sugar added individually.
In packaged foods, there is a whole science of masking the sugar and fat content to make it more addictive without triggering your inbuilt satiety mechanisms [1]. This is what today's engagement optimisers did for money in the 50/60s.
You could argue that these "innovations" were precisely to subvert the intuition that visual appearance of food (and other natural sensors) can be relied on to assess their nutritional properties.
> Most restaurants smuggle obscene amounts of butter
God I wish that was true. Butter is far too expensive to do that, so restaurants will use the cheapest alternative (usually soybean oil with butter flavoring) instead.
There is absolutely, unequivocally, 0 chance this can be accurate within any kind of reasonable bounds. I'm guessing you haven't done much calorie tracking if you think this could possibly be true.
I can make two dishes that look identical and have +/- 50% caloric content, easily.
> I expect a strong correlation between the visual appearance of food and its caloric content
This doesn't pass even simple scrutiny. There are so many caloric ingredients that aren't visible in food. You can't tell just by looking whether a rice dish contains half a stick of butter.
That’s not true. They have the same amount of calories roughly. It’s physically impossible for animal fat to have that many calories. Tallow has 900 calories per 100 grams while olive oil has 884. They are almost pure fat and pure fat has 9 calories per gram.
They are very different problems. You can attach every kind of sensor to the phone and get HD images, lidar scan, 3D model, heat signature and whatever other signal you want, but you still won't be able to figure out calories in a piece of food without breaking it apart at a molecular level. There's just too much hidden information. What sensor will tell you how many tablespoons of oil the chef used to fry onions for the sauce? Heck the chef himself probably won't be able to tell you.
I legitimately drove full month with near zero interventions in FSD. The second statement is achievable in my opinion. Most people have not experienced hw4 with latest releases.
That's an interesting comment, but I have driven in heavy rain, and it worked just fine. Can you share how you arrived at your conclusion? I mean there is a limit to where the obstruction is so intense that even human cannot drive I get that but its actually performing fine for me in heavy rain that is still drivable for a human.
That's unlikely. Try driving in a snowstorm, where visual inputs become effectively useless, and you quickly realize how much the motion inputs are factored in as well.
>But he looked around. “We were surrounded by people that were in their late 20s or 30s all day. And I realized that if I didn’t go to college, this is what life would be like.”
Lol, I can relate. I started working in an office when I was 16, now 24, and regretting wasting my youth grinding when I could have been having fun in a period of your life you only get to experience once.
Don't grow up too fast kids. Make stupid decisions and ride out your youth as long as you can afford to.
You're 24? Don't take this the wrong way but you have loads of time to do "youth shit."
As you get older, people expect you to be more competent in life and work. If you leave work for two years to bike around the world, it'll be a fabulous adventure and will in the grand scheme of things have little consequence down the road. Try that when you have a kid!
You're just defining your own fate here if you think 24 is so much older and different than 16. But also, perhaps your situation now would be different without the grind you went through? Instead of regretting anything I think you could just try to enjoy your youth now.
>>But he looked around. “We were surrounded by people that were in their late 20s or 30s all day. And I realized that if I didn’t go to college, this is what life would be like.”
Its just a marketing stunt. They complain about not getting into Harvard but he could literally rent a penthouse in Cambridge, hang out on the campus throw big parties and get 90% of the experience while supposedly running a 30M ARR company. Absolutely no benefit to actually enrolling except ego.
I understand the scepticism here. For sure this app isn’t 90% accurate in any traditional sense.
One note, as someone who also built a calorie tracking app with ai as well as lost a good amount of weight with it: accuracy for calorie tracking doesn’t matter. You can honestly just detect if it’s a meal and return 600 cals. For most people the simple fact that they become aware of what they eat and think about their food in an ongoing basis will lead them to loose Weight.
Sticking to it is the hard part.
It matters a lot if you have specific macro goals. If you don’t want to lose muscle, it is important to eat high protein especially during a cut. And keeping fat and/or carbs low while doing this is quite difficult without accurate data.
> You can honestly just detect if it’s a meal and return 600 cals.
That's ridiculous. What signal would that provide to the user? Let's say someone who is eating double the portions they should be eating. How will this hypothetical app help them figure that out?
> For most people the simple fact that they become aware of what they eat and think about their food in an ongoing basis will lead them to loose Weight.
And you think people will " become aware of what they eat" by shooting a picture of their food with an app which always say "600 cal"? I don't think you thought this through.
I'm working on an app in this area [1], and I've spent a lot of time exploring how to responsibly use AI for food tracking.
My conclusion is that while AI is excellent for augmenting your tracking experience, it's not yet reliable enough to be the sole tracking method. Consistency is key to successful food tracking, and AI can certainly help users avoid the common issue of missing a meal and losing momentum. However, inaccuracies, like consistently being off by 100-200 calories per day, can significantly impact results, especially for those on lower-calorie diets (like 1,200-1,500 calories/day, which is common for many women due to their physical size).
With FitBee I landed on communicating to the user that these are estimates and you probably shouldn't use it as your primary method of tracking calories.
If so then what a colossal waste of our planetary carbon budget. I don't know what the backend on this app is (maybe it was done properly i really hope so) but surely there is a solution which maintains or surpasses the accuracy of an LLM and uses <1% of the compute resources.
Like a small vision model combined with the size/measurements data from the AR sensors modern phones come with and an open source caloric values database should achieve the 90% accuracy they are claiming.
Ronald Wright writes about "progress traps" in A Short History of Progress. It's been awhile since I read that but I think about it more and more these days with AI products on the rise.
No, this is a completely unsolvable problem with just a camera.
You cannot differentiate a high calorie meal from a low calorie meal on sight alone.
The waste is selling a lie, enabled by AI bullshit artists and the public's seeming inability to understand that the US has no legal (or market most of the time) requirements to be truthful, upfront, or honest in marketing.
Like people just take this shit at face value and I don't understand how you can live in the US for more than a few years and not recognize that marketing is just lies, like not even smart or clever lies.
The app sucks, there’s no reason to use it when myfitnesspal is just leagues better. You can poison it and it will just follow the instructions as well.
I'm a college admissions consultant, and this doesn't surprise me at all. People don't realize how competitive the landscape has become. His test scores and GPA are average at the schools he applied to. Really you'd need to know how many APs he took and his AP scores to understand how colleges will treat his academic record.
To me, his college list indicates that he was mostly prestige hunting. There's nothing inherently wrong with that, but colleges can tell when a student wants to attend based just on branding. It comes across as if he wants to use college as a resume booster rather than as a place to grow.
The essay reads as a list of accomplishments, with little self-reflection. (Side note: referencing Steve Jobs is way overdone.)
Long story short, college admissions is not a VC pitch. If I had been this guy's advisor, I would have recommended he write an essay about something not related to Cal AI. Colleges will already know about the app from his activities list (and resume and, presumably, recommendation letters). There's a huge missed opportunity for him to write about something else.
The essays that worked for my students this year were often about more mundane topics that gave insight into their character. One of my favorites was from a student who started giving free haircuts to classmates. The essay implicitly shows that he's thoughtful and well-liked—someone you'd definitely want in your college community.
If he absolutely insisted on writing about Cal AI, I would have recommended that he write more about why he was inspired to build it and the human impact. Instead, he just rattled off metrics that admissions officers will likely know from other places in his app.
Talking about grindsets, ARR, DAU and getting up at 4:30am may be seen as good content for a twitter thread, but most grown adults cringe when they read copy and pasted fortune cookie wisdom memes.
I would agree, talking about actual human stuff related to an actually interesting topic was a wasted oportunity. Nobody actually cares what the numbers on the app are, least of all admissions officers.
American system of admissions to me seems so weird. Is it only there that unis accept mostly on extra things and not grades/test scores itself?
I'm Polish, here the only thing that matters is your final test scores, and nothing else. And I think it's same in the most of Europe and Asia too, right?
My impression is that American unis care way more about social aspect and so on, which I don't understand (but I guess it's a fine way of looking at things, too.)
The problem with the SAT is that too many people can score above 1500. In the 1500-1600 range, you might have only made 1-2 mistakes on the entire test -- it's more luck than skill at that point. You could maybe improve things by having a harder test for the elite schools, but the Asian model is not ideal either. I live in Japan, where many kids will spend their evenings in cram school (after a day of regular school) to prepare for the absurdly competitive college entrance exams. As I recall, South Korea actually restricts air travel on the day of their entrance exams so some kids won't be disadvantaged by being distracted by the noise of the overflight.
It's true that this model is more fair, and that's good, but it still feels wrong. There are way too many professions where you're de-facto locked out if you didn't get the right credentials at the right age, regardless of your practical skills. That results in us putting teenagers through these absurd trials for no real reason.
Parent already discussed this but at tier-one schools almost everyone (except legacy/athletic of course) has saturated the test score metric. Most applying have a max SAT or ACT. Most have a 4.0+ GPA. A 34 ACT score is in the bottom 40% of MIT applicants as far as I can tell.
The only thing that distinguishes applicants is the soft social stuff.
Japan and South Korea kind of fixed this problem with cram schools and ridiculously overtuned college admission exams. But e.g. KAIST isn’t really comparable to MIT.
So is this the case of final exams being too easy and unis having to adjust around that?
Or is it that way because of some other factors? I was thinking how much of this is because of historical factors; I assume in times before standarised exams it would be a very convinient way of finding new students.
But then, I don't know how it was historically in Europe/Asia.
It's because a good majority of these schools have thousands of applicants who might as well be perfect across the board grade and test scores wise, so its either they flip a coin, or choose some other standard.
The tests need to be harder, but people would complain.
I didn't study for the ACT at all (literally went in without knowing anything about it) and got a 35. It's a trivial exam.
What you're saying doesn't make any sense, do you just enjoy bragging? Hardness of a task only makes sense in the context of who is doing the task. The fact that you scored highly means it was not a hard test for you compared to the average test taker. I could not determine this without the average score.
They're not bragging. They're pointing out that the ceiling is dramatically too low, which has caused elite universities to spend decades creating more and more elaborate and more and more detached and meaningless gatekeeping mechanisms. The national average does not matter in the context of the nation's most competitive schools.
The fact that the average score for Harvard and similar for other elite colleges for the ACT is 34-35 means that the national average is worthless for the purposes of elite colleges. Majority of people who would even bother to apply for them are basically perfect across the board grades wise, so its worthless to brag about it.
Bar making exams harder, the only other way is subjective methods. I detest subjective methods, but making exams harder is very unpopular
For ever 100 applicants 3 seats are available. If you are "average" amongst the pool of applicants there are 46 better people than you that won't get in either.
Having elite universities scale up the number of seats available can be done. Grow the pie instead of having the current scarcity mindset. This would actually solve much of the current problems. There is no reason you cannot have the same or better quality of education with more students per university. The only reason this problem exists is that by limiting the number of seats you create artificial scarcity and thus higher value.
Just because it doesn't surprise you doesn't mean it's okay. You have to acknowledge that as an admissions consultant you're part of a small gatekeeping community bubble. Even though I attended one of these schools, I can recognize that universities have been rapidly losing their credibility, and this is only going to accelerate that trend. And by the way, this person is probably more accomplished than I am, even though I am now quite a bit older and my essay was apparently good enough to tick off the checkboxes.
The question you need to be asking is how the university system made an enemy out of someone who is clearly one of the most talented members of his age cohort in the nation. That's a failure no matter how hard you try to explain or justify the status quo. It's time for some real accountability and soul searching from the system, not excuses. Trying to nit pick the essay and pointing out how he should have done X or Y instead is completely missing the point.
There was an HN story some years ago about the guy who created homebrew -- a Mac app used by a plurality of Google employees -- being rejected from a job at Google. This seems to follow that pattern: it's not enough that you achieve great things and talk/write about your achievement, you have to stroke the egos of people who could have never accomplished what you did, but still have the power to judge you because the bureaucracy has given them that power.
If the $30M ARR number is true, it's not hard to understand why he wants to talk about it as much as possible. Maybe if you come from family money, you can hear that kind of figure and yawn -- but as someone who came from poverty, I can tell you that this is like if the kid built a rocket out of spare parts in his garage and visited the moon. There's no words for how stunning this is, and everything else in his life must seem trivial by comparison.
I can't understand why the admissions officers would rather read an essay about a kid who volunteered at an animal shelter or something. Anyone can do that.
It has been trendy in Silicon Valley recently to use inappropriate accounting methods to measure ARR.
Joe, a regular guy: Makes $120k at his desk job
Joe, the businessman: Made $20k in 32 days, $228k ARR
Joe, who launched 5 months into development and did 60k in the first 2 weeks: $1.5M ARR
In all three of these examples, Joe's financial outcome is the same. This business does not have any longevity, and all of its revenue is from converting paid advertising of various kinds. It's still impressive, but is most likely a >10x exaggeration on even the lifetime revenue he makes from this. Which is of course circular, because the reason he's doing all this is to make a business out of monetising the audience of people who want to make money.
All of this is clever social climbing, but is clever social climbing the thing that should be rewarded by colleges?
um - I would. Colleges don't want to get panned for hiring a scam artist which is exactly what this is. Unlike VC where that skill is slightly revered.
The app is fake - at best its puffery, and the essay was littered with grammatical errors.
I think the average American today, including the average admissions officer, has a negative view of technology. So, an application that is unequivocally optimistic about technology is unlikely to be well received. I think that that is what happened here. We also have no visibility into letters of recommendation, which are likely a big factor.
This is an incredibly poor take - curious as to how you just completely made up that ridiculous claim? Ironic as well that you think letters of recommendation matter for college admissions when they are perfunctory for probably > 95% of them. Maybe you shouldn't espouse your opinions on this.
I mean, maybe he deserved to get into more universities, but he did get into solid universities, even if they’re not at the very top. The application pool is very competitive at top universities, and I’m not sure business success should be an automatic in.
Surely this sort of thing happens all the time? Not to excuse it, but I really don't think any of those rejections was intended to be the personal attack he thinks it is.
I'll bite - I'm an early adopter, and paying user, I paid for the year, but won't renew. For what it's worth, the app UI is dead simple and it makes it easier to track macros. I'll adjust the inputs to what I know I'm eating, and I rarely depend on the "AI camera" I usually just use the UPC barcode scanner. I'm mainly focused on protein intake and making sure I hit those goals. It does a decent job with simple foods, which is healthier for me to eat. I'll break each ingredient down, combine them into meals, then save them. Rinse and repeat for tracking. It's better than a spreadsheet, and I get to see the photos of what I'm eating.
That being said, I'm not going to renew next year. But there is something to this product that is not the "AI" but the simplicity vs. MyFitnessPal which has a ton of features I don't really need.
The critiques are good, but for me, the simplicity of the app is the most attractive part for me.
A friend of mine build a similar app last year (https://joineat.app) and it didn't go anywhere (even though it is objectively the nicer app). So there's a lot of luck involved here as well (or maybe he was too early).
For your friends app, I had to go into the app store and then expand the description to view the key features, where it is mentioned that it uses AI similarly as Cal AI. Just based off the initial images of Eat compared to Cal AI, then it's much more clear what Cal AI does compared to yours (besides plastering AI everywhere).
Another thing I noticed is that I saw a random guy on instagram with a rather big following being sponsored by Cal AI. Maybe your friend was unsuccessful in getting his app out there? Although I agree that luck will always play a role, but if the public don't understand what your app immediately does and they believe AI to be pure magic, then sprinkling that everywhere will get something like Cal AI flying.
I still think it is shit from a technical perspective in terms of the validity of amount of calories from a single image and nothing else. But it seems like that's not what people want, inherently because they are lazy. Actually counting calories is much harder long term. If regular people now think that this is magically replacing this process by just snapping a picture of their processed meal, then I can see why it's successful. Although quite depressing...
I thought about doing this years ago, but without AI, the only way was to have people do the analysis. I thought this was bad karma, as I would end up paying people in Bangladesh to look at the stuff that Americans eat.
A lot of what Americans eat is kinda grim? I couldn't eat the sausage at the hotel breakfast in Little Rock this morning because it tasted like new vinyl smells.
Wrt Bangladesh... I imagine the job might be a little harder during Ramadan.
My understanding is that even nutrition packaging is often off by up to 30%. Sorry, no source, just what I’ve heard a number of times. If I want to diet I typically build this in and it works well. If they’re actually off by 10% that’s not terrible.
But I tried one of these apps years ago and it went a step further than photos. It used the front facing camera on iPhones to build a 3d model of the food and measure its volume as well. Even that was off by more up to 50% not 10%.
The interesting thing I found, and it’s obvious when you read it but not when you’re trying to diet, is if you don’t layer food on top of itself or other food, you (and a camera based calorie counter) will have a much better understanding of how much you’re eating. Bowls / mounds of food will deceive you.
NIST says "in general NIST’s measurements are accurate to within 2% to 5% for nutrient elements (such as sodium, calcium and potassium), macronutrients (fats, proteins and carbohydrates), amino acids and fatty acids. Its measurements are accurate to within 5% to 10% for water-soluble vitamins (such as vitamin C) and 10% to 15% for fat-soluble vitamins (such as vitamin D)." https://www.nist.gov/how-do-you-measure-it/how-do-you-know-y...
Maybe there's something where they're off by 30%, but how many people even track how much vitamin D they get from food?
Standard for cutting is about 500 calories deficit, for 1lbs lost a week. Lets say 2500 calories daily standard. That's 20%. If food packaging was off by 30%, food nutrition planning would be worthless, but we know it isn't because we see fairly consistent results from weightlifters (assuming they're actually weighing their food and not eyeballing/using a PoS app like this)
> The concept is simple: Take a picture of the food you are about to consume, and let the app log calories and macros for you.
> The result is an app that the creators say is 90% accurate, which appears to be good enough for many dieters.
It absolutely cannot be "90% accurate". But I'm sure it seems "90% plausible" to its millions of users.
Incredible that a product like this can exist. Do people just will the fiction into reality?
Incredibly, these are the types of app ideas you'd hear from non-tech "entrepreneurs" in 2012 looking for a co-founder. The problem being, the engineers knew it was impossible. You could fake it I guess by asking Google to search for "similar photos" and getting a plausible calorie count half the time. But the users wouldn't believe it.
We're now at the phase where any impossible idea can be fully marketable by slapping "AI" in the name. ChatGPT feels so magical that we now believe unicorns really do exist.
Just read the Google Play reviews, the app still has a long way to go to be usable.
But it's still a great idea.
Also, they should calculate both the calories and power requirements for each meal analyzed. What I mean is, it should says something like: this burger has 800 kcal and the analysis consumed 1kw of datacenter power. ;)
kw is an instantaneous measurement. Energy usage would be kWh (kilowatt-hours). Considering it would take a tiny fraction of a server’s compute for less than a second this would be very small.
It has $2m revenue, so it's clearly a great idea (at this stage?) financially and 'people love it' (30% retention)
Technically it's a garbage idea, and I'd say they could get class-actioned without good T&Cs. It's literally impossible to determine the sugar and fat content of a meal.
I'd never make it for the latter reason, however you clearly need to believe in the former to make it big haha.
30% retention means that 70% of people who have paid for it didn't consider it valuable enough to pay for.
The $2m figure is unverified but, even if it was, turnover is meaningless without knowing their expenses. If they're burning through £2.1m in LLM compute and marketing then they're losing money.
Plus, the guy seems like a dick so I'm taking his story with an enormous pinch of salt.
The bird thing was at least _possible_, though, to a reasonable level of accuracy. What they're claiming to do here is completely impossible; there is simply no way of even vaguely accurately determining the calorie content of food based on a picture of the food.
Seems contradictory that there's a market for this since it requires the same individual to simultaneously be concerned about precisely measuring calories yet willing to pay for a method of doing so that's (probably) wildly inaccurate.
The comments from HNers in this case are interesting.
Usually if a teenage hacker builds something, the HNers would respond with enthusiasm, but then, this is a guy who builds *something* and *actually* makes a good business out of it, at the same time maintains his high school life, and all we have is skepticism and discouragement.
The obvious problem with this is how can it tell how large your meal is or how much butter you put in? I can see it working for fast/junk food, though.
When I learnt machine learning one of the things was continually training the model. Like your spam filter. You show it what is spam and eventually it learns. Is this stuff continually trained on the user's BMI? That's the only way to tell if a diet is working. Or is it just making absolute claims based on universal training data?
Been keeping a food diary for several months now. I did have to spend a bit of time at the beginning working out the calorie content of the food I eat. But after that it's mostly just copy + paste - turned out I was far more of a creature of habit than I thought.
If you want to derive any benefit from doing this you should really be trying to get your numbers correct from the start. I wouldn't leave that to a LLM.
He should have just written #BLACKLIVESMATTER 100 times, because that's apparently all it takes to get into Stanford. Honestly though college essays are a bit of a joke, reviewing hundreds of them sounds like torture. The lack of rigor is probably the point though, since it gives the admissions process flexibility to ensure that legacy students get in and they meet their DEI targets.
(1) That is the paradigm of classification, don't knock it, and
(2) I did some work on a pre-product startup that wanted to build something like this about 10 years ago, when visual recognition was much less developed.
Anyone who has participated in calorie-tracking for an extended period of time can tell you that the visual appearance of food can be highly misleading to the number of calories in it.
I'm all for making it easier for people to lose weight but this app may honestly have the reverse effect. If the app estimates calories too low (and therefore the individual eats more), many people will get frustrated with the lack of progress and give up. If the app estimates too high, the individual will lose weight, but diet fatigue and other negative side effects of being at a >500 calorie deficit may make the diet too difficult to maintain.
I actually went over this recently with someone who wanted to build something similar. The conclusion was this is a very difficult problem to solve, probably intractable to some extent. You can't see the complete composition of the food with a standard camera. E.g. I make a salad which is maybe 300 calories. Then I sprinkle some croutons and bacon on top, which will mostly be in the middle. Then I put dressing on it, which is hard to estimate. That dressing hides the bacon and croutons and, since it contains a lot of oil, could seriously skew the measurement one way or the other. Now I mix it all around and the AI can't tell how much dressing was used at all.
I pick this example because I've seen specifically this cause problems for people trying to lose weight. They think their eating a salad, not realizing they've thrown an extra 500 calories on top.
Another case: I sit down to breakfast, having made myself eggs and toast. One of if not the largest contributor to my calorie intake will be the amount of butter on my toast. If I use four pats that will probably exceed my calorie intake from eggs. If I use one, not as much. I sincerely doubt it's realistic to tell the difference with any sort of precision.
Flashback to "Real Men of Genious" ads ... "Here's to you, Mister Giant Taco Salad Inventor."
https://www.youtube.com/watch?v=fXWq2AVlrsY
A lot of the testimonial photos for this show the AI literally deciphering the text Nutrition Information label.
Any other interpretive situation based solely on a camera has so many inherent flaws as to render this almost useless.
I think even if you have volume factored in like photogrammetry/lidar, the inside of the food could be something else too like a chunk of meat inside potatoes
The nutritional information label that lists the calories in the food? What is the point of that?
Steelmanning this: You take your phone out and snap a picture and it gets added to a running total without typing into a tiny keyboard or doing any math. You consult your total next time you're thinking of eating.
Critiquing: You still need to figure out serving sizes - it's going to need to ask how many servings. Nutrition labels also aren't available for any number of things.
Anecdote of one... about 8 years ago I put a lot of effort into losing weight... when I was eatng a 1500 calorie/day diet, I wasn't losing weight... per a nutritionist friend who looked at what I was eating suggested closer to 2800 (6'1" tall, 370# at the time) and when I did, I started losing weight. Note this was combined with crossfit 3-4 days a week both on the lower and higher calorie intake.
If you have a really dysregulated metabolism, your body can definitely work against you when consuming too little.
Had a friend who came to me with the same idea. In challenge of the idea I sent a picture of some chopped cucumbers and tomatoes, and an other picture with the same chopped vegetables drizzled with a copious amount of olive oil. I asked if they can tell which one is which. The difference was hundreds of calories and you could not tell which one is which (least of all how much oil there is on the one with the oil.)
That of course feels like a "weird" edge case, but it illustrates the general problem that butter/oil/sugars can pack a lot of calories and have no or almost no visual signature.
That's not a weird edge case at all. Adding oil to food is one of the most common ways to add calories (intentionally or not).
A salad wouldn't even be the hardest case to detect, since raw vegetables don't soak up as much oil as other kinds of food.
You're right, but I think the general public is largely ignorant about calories and nutrition. Even basics like 4 cals per gram of protein and carbohydrate, 7 for alcohol, 9 for fats. Or even what a carbohydrate really is versus a "sugar", which people talk about as bad.
There's a sweet spot for an app that is inaccurate with a market that wants it but doesn't understand how inaccurate it is.
Kind of like how I could vibe code an app, get it to "work", think it's great and be ignorant of the many ways it will break or isn't working that a knowledgeable developer could.
The general public's understanding of food is still stuck in 1990s "destroy all fats (and completely ignore the sugar we replaced it with)" diet culture.
The fact that people still believe in reducing fat as it's own goal (instead of being an easy way to reduce calorie content) is a testament to how bad the public is at identifying fact from fiction.
Then you have shit like the influencer foods, "Feastables" and "Hydration beverage" Prime, which is just flat soda. It's pathetic.
Or think of all the dude bros who insist on dry scooping cup fulls of protein+caffeine powder, and going home to gorge themselves on two pounds of chicken breast, and yet doing absurdly normal amounts of weightlifting or exercise that requires no modifications to their already protein overloaded American diet.
Diet culture is what is fucking American health. People read fucking tabloids that bad-faith regurgitate poorly done "science", funded by the council for selling more food, and insist that since "Woman's Health" says that scientists say chocolate both kills and saves you, scientists are dumb and know nothing, even though THE ACTUAL SCIENCE NEVER CONCLUDED ANYTHING, because the scientific paper was just an observational study!
Related is the fear some have of Saturated Fats and Meat. So many people don't even realize that the body does need some Saturated Fats, or that fats are often a mix of them and vary by the species, breed and how they're fed.
It doesn't help in how far some foods have been bred in the past century and a half in particular. Or how different people with different genetics may react to certain foods.
Everyone keeps using this example, but you have the exact same problem calorie counting any food that might be lathered in fat. It's why people underestimate their calorie intake by 30%+.
You could level the same criticism at Cronometer and MacroFactor when you try to log food you received at a restaurant. Yet those apps are still useful (and I think requisite) for knowing what you're eating. And you should probably 1.5x the calorie estimation when you eat out.
What's interesting is whether this app can accurately estimate food at all. If it can, then that's a huge win and you can add your own buffer zone for oils like you already have to do when you count calories. ...Or chill on the butter and restaurant food when you're supposedly trying to lose weight.
> Everyone keeps using this example, but you have the exact same problem calorie counting any food that might be lathered in fat.
Not really. In practice you need to know the ingredients to estimate the caloric value. Either because you prepared the meal, or because someone who wrote the recipe of it calculated and wrote it on the packaging/menu.
> If it can, then that's a huge win
But that's the point of the example. That it can't. If it could, that would be good. But it can't do it, and not because the app is deficient in some way, but because the necessary information is not available in the image.
> Or chill on the butter and restaurant food when you're supposedly trying to lose weight.
Yes of course. And that is one of the things you learn when you do calorie counting. The practice drives home that message, and many others. But you are not going to learn that if the app hides the signal from you.
> What's interesting is whether this app can accurately estimate food at all.
Spoiler: It can't. It is physically impossible to determine calories from pictures of food.
> In challenge of the idea
This was technically correct but missed out on a viral app and millions of revenue?
That just sounds like the difference between a salad with and without dressing on it. Maybe not so weird.
The 1st issue I'd think of would be scale.. eg. identical looking plate of food in EU vs USA. The images might look identical but the USA one would be scaled up and contain much more calories. Everything that could be in the image for scale reference would also be scaled up along with the food.
This is where something like a fork on the plate/bowl might help.
Many people will analyze this from a tech perspective. I urge you not to. This isn't about whether the technology is good or bad. The real reason they succeeded is their mastery of marketing, particularly TikTok and influencer marketing. Understanding distribution is far more important than knowing how to build something, and this is truer now than ever before. I know it stings but its the truth.
I didn't analyze this for either: rahter what is what is the typical outcome for young humans who achieve a high degree of success/fame before their prefrontal cortex is fully formed.
As we understand more about brain development in kids, I think and under studied aspect are kids who got access to a lot more money than normal typical kids have, and the results such wealth brings.
> I think and under studied aspect are kids who got access to a lot more money than normal typical kids have, and the results such wealth brings.
As opposed to the kids born on planets without atmospheric oxygen, of course. Those kids don't stand a chance.
There's always some advantage others have. Money, good looks, distribution, connections, right place right time.
"Wealth inequality" isn't going to disappear overnight, and lamenting about it won't get us closer to success.
We're all dropped into the Darwinian gradient landscape. Some of us have better starting positions. While we sit and wait for policy decisions to make things easier, our job remains to find gradients that aren't too steep, aren't over-explored by the masses, and that give us some modicum of joy to spend our lives upon.
The minnows and gazelles have it much worse than us. Praying mantises, anglerfish, and the hosts for the parasitoid wasps are practically living in a daily Kafkaesque horror. Meanwhile we're in our own dopamine drip Disneyland with near-infinite degrees of freedom and plenty of years on the clock (for most of us).
Seneca said some good things about this.
I think you missed the part about "[achieving] a high degree of success", in particular the achievement. They are referring to young people who make a successful business rather than those who are born to parents who made a successful business.
The point of looking at this from a technical perspective though is that the underlying tech doesn't actually work, and it's just a smoke and mirrors game built on marketing.
Like Theranos. And Nikola. And Fyre Festival. Etc.
Age is irrelevant, unless we're trying to tell youngsters that fraud is an acceptable means to get ahead in life. But then again given our current political environment maybe that is what we're trying to tell the next generation.
EDIT: the app now also just reads nutrition labels as a backstop. Nutrition labels already include the calorie data, so the app isn't doing anything there.
> But then again given our current political environment maybe that is what we're trying to tell the next generation.
There's no trying.
The US has played "Just grift your way to money" as a standard means of operating since at least the dotcom boom. A reason so many young and poorly educated people jump at obvious MLM type scams and other scams is because they feel that everything is a scam, so surely they can get in on it too, right?
And everything IS a scam. Coke doubled in price in the past 5 years. I promise you their costs did not double. Their costs are Labor (highly automated), water (they almost always have sweetheart deals for dirt cheap water, cheaper than you pay), and one of the most subsidized commodities available, HFCS, or alternatively, a sprinkle of dirt cheap chemicals for their diet sodas.
People feel that, even when they don't understand or even recognize it.
People recognize that the US has been a scammy free for all for decades now. Everyone for themselves, fuck you, got mine.
We are on like the third generation raised this way. The people who took "Greed is good" to heart had kids, and raised them with it as a core principle.
Jordan Belfort, the guy who Wolf Of Wall Street is based on and spent time in prison for scamming his clients in basically the same way modern crypto pump and dumps work, now sells out auditoriums as a motivational speaker for fucks sake.
The kids LOOK UP TO SCAMMERS
My reasoning for evaluating the relevancy of this app:
1. If the food being scanned has a nutrition label, I don't need this app.
2. If there's no nutrition label, the app can't possibly extrapolate the nutritional information. It can't estimate portion size or the ingredients in the recipe.
3. If the app can't extrapolate nutritional information, I don't need this app.
4. I don't need this app.
It's not about being right, it's about appearing to be right
> It's not about being right, it's about appearing to be right
What you need is a LLM.
Isn't this basically what they used, a multimodal AI?
I think the key insight here is that actually counting calories is not needed by the app's demographic. Possibly just getting them to pay attention to what they are eating is enough for them to see progress or at least feel like they are doing something.
Recently I have started running dish descriptions through deepseek-r1:8b to give a rough estimate on calories and it is sufficient, at least for my cooking. Of course this will hallucinate on complex cases, and arguably simple dishes are easy to count. Still, counting by hand is tedious compared.
I am happy with a rough number on a dish, I do not need precision to know if I am not eating enough calories. Note there are errors on the result and reasoning, but still this dish should be around the ballpark of 500 cal. I figure running this through a larger model might be more accurate. I wondered if maybe I wanted to create an app for that, but I am happy not to.
Yes, simple descriptions could be parsed with NLP, and yes, calories could be inferred with a database.
[flagged]
Money and fame aren't everything.
Some people have values and morals that they live by.
I don’t see why you believe 2 would be true. I expect a strong correlation between the visual appearance of food and its caloric content etc.
This is completely wrong. For example, you can increase the amount of oil or butter in a recipe, doubling or tripling its calorie count, and you would never be able to tell from a picture.
I imagine it just autofills the information and then you can edit it to make it more accurate
You'd have to be kind of stupid to expect it to actually be 100% accurate for all meals
The point of the app is to figure out the calories of a meal automatically by taking a photo.
Without knowing the amount of sugar, butter, oil, etc. is used in a dish, one cannot know if a dish is worth 250 kilocalories or 750 kilocalories.
If I need to manually fill in details of ingredients and amounts to get to the calories to be have an error margin of less than 100%, then the app is not useful and is at best misleading.
... So if you already know the answer you can correct it? I mean, what possible use is that?
Therefore...
4. I don't need this app.
Most restaurants smuggle obscene amounts of butter and sugar into dishes to make them more delicious so you'll come back. It's not unreasonable to assume that every subcomponent of a recipe might have sugar added individually.
In packaged foods, there is a whole science of masking the sugar and fat content to make it more addictive without triggering your inbuilt satiety mechanisms [1]. This is what today's engagement optimisers did for money in the 50/60s.
You could argue that these "innovations" were precisely to subvert the intuition that visual appearance of food (and other natural sensors) can be relied on to assess their nutritional properties.
[1] https://en.m.wikipedia.org/wiki/Bliss_point_(food)#:~:text=T...
> Most restaurants smuggle obscene amounts of butter
God I wish that was true. Butter is far too expensive to do that, so restaurants will use the cheapest alternative (usually soybean oil with butter flavoring) instead.
There is absolutely, unequivocally, 0 chance this can be accurate within any kind of reasonable bounds. I'm guessing you haven't done much calorie tracking if you think this could possibly be true.
I can make two dishes that look identical and have +/- 50% caloric content, easily.
> I expect a strong correlation between the visual appearance of food and its caloric content
This doesn't pass even simple scrutiny. There are so many caloric ingredients that aren't visible in food. You can't tell just by looking whether a rice dish contains half a stick of butter.
Or if it's diet coke or regular coke. Yes, it's drinks, not food, but the same concept applies.
They claim 90% accuracy, whatever that means, but I have my doubts regarding it's usefulness.
Try telling a picture of diet coke from regular coke apart.
How does an app know that this piece of chicken cordon bleu is actually filled with more bacon and cheese than chicken?
1 tbsp of animal fat has about 900 calories.
1 tbsp of olive oil has 135 calories.
How would the app know which fat the food was cooked in?
> 1 tbsp of animal fat has about 900 calories.
This is extremely false. Please verify your sources better (and apply a skosh of critical thinking).
> 1 tbsp of olive oil has 135 calories.
This is false too, but at least it's in the right ballpark.
> This is extremely false. Please verify your sources better
Sorry! I was using Cal AI
Ok, that made me laugh.
That’s not true. They have the same amount of calories roughly. It’s physically impossible for animal fat to have that many calories. Tallow has 900 calories per 100 grams while olive oil has 884. They are almost pure fat and pure fat has 9 calories per gram.
“You can count calories and sugar content of the meal using just a camera”
“You can have a full self driving car with just a few cameras”
In a way both things are very much similar and the real accuracy is more of a fiction than reality.
They are very different problems. You can attach every kind of sensor to the phone and get HD images, lidar scan, 3D model, heat signature and whatever other signal you want, but you still won't be able to figure out calories in a piece of food without breaking it apart at a molecular level. There's just too much hidden information. What sensor will tell you how many tablespoons of oil the chef used to fry onions for the sauce? Heck the chef himself probably won't be able to tell you.
Hyperspectral camera?
I legitimately drove full month with near zero interventions in FSD. The second statement is achievable in my opinion. Most people have not experienced hw4 with latest releases.
FSD with just cameras for input breaks down in times of low visibility (fog, smoke, heavy rain). That’s a straightforward fact
That's an interesting comment, but I have driven in heavy rain, and it worked just fine. Can you share how you arrived at your conclusion? I mean there is a limit to where the obstruction is so intense that even human cannot drive I get that but its actually performing fine for me in heavy rain that is still drivable for a human.
Self driving car is far more plausible, we drive cars with visual input alone. But a camera can't chemically analyse the insides of your dish.
That’s exactly the point. We drive cars with visual input alone and have so many crashes, injuries and deaths every day.
> we drive cars with visual input alone.
That's unlikely. Try driving in a snowstorm, where visual inputs become effectively useless, and you quickly realize how much the motion inputs are factored in as well.
>But he looked around. “We were surrounded by people that were in their late 20s or 30s all day. And I realized that if I didn’t go to college, this is what life would be like.”
Lol, I can relate. I started working in an office when I was 16, now 24, and regretting wasting my youth grinding when I could have been having fun in a period of your life you only get to experience once.
Don't grow up too fast kids. Make stupid decisions and ride out your youth as long as you can afford to.
You're 24? Don't take this the wrong way but you have loads of time to do "youth shit."
As you get older, people expect you to be more competent in life and work. If you leave work for two years to bike around the world, it'll be a fabulous adventure and will in the grand scheme of things have little consequence down the road. Try that when you have a kid!
You're just defining your own fate here if you think 24 is so much older and different than 16. But also, perhaps your situation now would be different without the grind you went through? Instead of regretting anything I think you could just try to enjoy your youth now.
>>But he looked around. “We were surrounded by people that were in their late 20s or 30s all day. And I realized that if I didn’t go to college, this is what life would be like.”
Its just a marketing stunt. They complain about not getting into Harvard but he could literally rent a penthouse in Cambridge, hang out on the campus throw big parties and get 90% of the experience while supposedly running a 30M ARR company. Absolutely no benefit to actually enrolling except ego.
I understand the scepticism here. For sure this app isn’t 90% accurate in any traditional sense.
One note, as someone who also built a calorie tracking app with ai as well as lost a good amount of weight with it: accuracy for calorie tracking doesn’t matter. You can honestly just detect if it’s a meal and return 600 cals. For most people the simple fact that they become aware of what they eat and think about their food in an ongoing basis will lead them to loose Weight. Sticking to it is the hard part.
It matters a lot if you have specific macro goals. If you don’t want to lose muscle, it is important to eat high protein especially during a cut. And keeping fat and/or carbs low while doing this is quite difficult without accurate data.
This app isn’t for those people. Most people don’t have macro goals.
> You can honestly just detect if it’s a meal and return 600 cals.
That's ridiculous. What signal would that provide to the user? Let's say someone who is eating double the portions they should be eating. How will this hypothetical app help them figure that out?
> For most people the simple fact that they become aware of what they eat and think about their food in an ongoing basis will lead them to loose Weight.
And you think people will " become aware of what they eat" by shooting a picture of their food with an app which always say "600 cal"? I don't think you thought this through.
I considered another app with a buddy but we never build it. A food diary for people with medical problems.
Take a picture of everything you eat and correlate it with symptoms. Have AI figure out what may be a trigger.
(I have a super rare food disease that took years to figure out and made my life unbearable).
I'm working on an app in this area [1], and I've spent a lot of time exploring how to responsibly use AI for food tracking.
My conclusion is that while AI is excellent for augmenting your tracking experience, it's not yet reliable enough to be the sole tracking method. Consistency is key to successful food tracking, and AI can certainly help users avoid the common issue of missing a meal and losing momentum. However, inaccuracies, like consistently being off by 100-200 calories per day, can significantly impact results, especially for those on lower-calorie diets (like 1,200-1,500 calories/day, which is common for many women due to their physical size).
With FitBee I landed on communicating to the user that these are estimates and you probably shouldn't use it as your primary method of tracking calories.
[1] https://apps.apple.com/us/app/fitbee-calorie-macro-counter/i...
Am i right in assuming this is app is just an openai prompt wrapped as a app?
If so then what a colossal waste of our planetary carbon budget. I don't know what the backend on this app is (maybe it was done properly i really hope so) but surely there is a solution which maintains or surpasses the accuracy of an LLM and uses <1% of the compute resources.
Like a small vision model combined with the size/measurements data from the AR sensors modern phones come with and an open source caloric values database should achieve the 90% accuracy they are claiming.
Ronald Wright writes about "progress traps" in A Short History of Progress. It's been awhile since I read that but I think about it more and more these days with AI products on the rise.
No, this is a completely unsolvable problem with just a camera.
You cannot differentiate a high calorie meal from a low calorie meal on sight alone.
The waste is selling a lie, enabled by AI bullshit artists and the public's seeming inability to understand that the US has no legal (or market most of the time) requirements to be truthful, upfront, or honest in marketing.
Like people just take this shit at face value and I don't understand how you can live in the US for more than a few years and not recognize that marketing is just lies, like not even smart or clever lies.
The app sucks, there’s no reason to use it when myfitnesspal is just leagues better. You can poison it and it will just follow the instructions as well.
Not sure if it made it to hn, but the founder recently got rejected from a number of top universities, despite clear talent:
https://x.com/zach_yadegari/status/1906859987105636667
https://x.com/zach_yadegari/status/1906888487292559531
I'm a college admissions consultant, and this doesn't surprise me at all. People don't realize how competitive the landscape has become. His test scores and GPA are average at the schools he applied to. Really you'd need to know how many APs he took and his AP scores to understand how colleges will treat his academic record.
To me, his college list indicates that he was mostly prestige hunting. There's nothing inherently wrong with that, but colleges can tell when a student wants to attend based just on branding. It comes across as if he wants to use college as a resume booster rather than as a place to grow.
The essay reads as a list of accomplishments, with little self-reflection. (Side note: referencing Steve Jobs is way overdone.)
Long story short, college admissions is not a VC pitch. If I had been this guy's advisor, I would have recommended he write an essay about something not related to Cal AI. Colleges will already know about the app from his activities list (and resume and, presumably, recommendation letters). There's a huge missed opportunity for him to write about something else.
The essays that worked for my students this year were often about more mundane topics that gave insight into their character. One of my favorites was from a student who started giving free haircuts to classmates. The essay implicitly shows that he's thoughtful and well-liked—someone you'd definitely want in your college community.
> huge missed opportunity for him to write about something else
When you are locked in and have the grindset there is nothing else.
If he absolutely insisted on writing about Cal AI, I would have recommended that he write more about why he was inspired to build it and the human impact. Instead, he just rattled off metrics that admissions officers will likely know from other places in his app.
Talking about grindsets, ARR, DAU and getting up at 4:30am may be seen as good content for a twitter thread, but most grown adults cringe when they read copy and pasted fortune cookie wisdom memes.
I would agree, talking about actual human stuff related to an actually interesting topic was a wasted oportunity. Nobody actually cares what the numbers on the app are, least of all admissions officers.
American system of admissions to me seems so weird. Is it only there that unis accept mostly on extra things and not grades/test scores itself?
I'm Polish, here the only thing that matters is your final test scores, and nothing else. And I think it's same in the most of Europe and Asia too, right?
My impression is that American unis care way more about social aspect and so on, which I don't understand (but I guess it's a fine way of looking at things, too.)
The problem with the SAT is that too many people can score above 1500. In the 1500-1600 range, you might have only made 1-2 mistakes on the entire test -- it's more luck than skill at that point. You could maybe improve things by having a harder test for the elite schools, but the Asian model is not ideal either. I live in Japan, where many kids will spend their evenings in cram school (after a day of regular school) to prepare for the absurdly competitive college entrance exams. As I recall, South Korea actually restricts air travel on the day of their entrance exams so some kids won't be disadvantaged by being distracted by the noise of the overflight.
It's true that this model is more fair, and that's good, but it still feels wrong. There are way too many professions where you're de-facto locked out if you didn't get the right credentials at the right age, regardless of your practical skills. That results in us putting teenagers through these absurd trials for no real reason.
Each university could provide a custom entry exam to ensure the test is unique and difficult enough to not be gamed as easily
People are so much more than the single number abstracted from 6 hours of exams.
Parent already discussed this but at tier-one schools almost everyone (except legacy/athletic of course) has saturated the test score metric. Most applying have a max SAT or ACT. Most have a 4.0+ GPA. A 34 ACT score is in the bottom 40% of MIT applicants as far as I can tell.
The only thing that distinguishes applicants is the soft social stuff.
Japan and South Korea kind of fixed this problem with cram schools and ridiculously overtuned college admission exams. But e.g. KAIST isn’t really comparable to MIT.
So is this the case of final exams being too easy and unis having to adjust around that?
Or is it that way because of some other factors? I was thinking how much of this is because of historical factors; I assume in times before standarised exams it would be a very convinient way of finding new students. But then, I don't know how it was historically in Europe/Asia.
It's because a good majority of these schools have thousands of applicants who might as well be perfect across the board grade and test scores wise, so its either they flip a coin, or choose some other standard.
The tests need to be harder, but people would complain.
I didn't study for the ACT at all (literally went in without knowing anything about it) and got a 35. It's a trivial exam.
What a douchey thing to say. You know the average score is like 20 right? Its definitely not trivial
The average for the SAT is 1050 https://satsuite.collegeboard.org/scores/what-scores-mean/wh...
I got a 1040 on the SAT in the 5th grade. The average score is useless for gauging how hard these exams are.
Bragging how you got a 34 on the ACT or 1450+ on the SAT for an elite college is like bragging about clubbing a seal
What you're saying doesn't make any sense, do you just enjoy bragging? Hardness of a task only makes sense in the context of who is doing the task. The fact that you scored highly means it was not a hard test for you compared to the average test taker. I could not determine this without the average score.
They're not bragging. They're pointing out that the ceiling is dramatically too low, which has caused elite universities to spend decades creating more and more elaborate and more and more detached and meaningless gatekeeping mechanisms. The national average does not matter in the context of the nation's most competitive schools.
The fact that the average score for Harvard and similar for other elite colleges for the ACT is 34-35 means that the national average is worthless for the purposes of elite colleges. Majority of people who would even bother to apply for them are basically perfect across the board grades wise, so its worthless to brag about it.
Bar making exams harder, the only other way is subjective methods. I detest subjective methods, but making exams harder is very unpopular
> His test scores and GPA are average at the schools he applied to.
Average is quite a bit above the floor though, so that just makes it sound like he should have been accepted.
For ever 100 applicants 3 seats are available. If you are "average" amongst the pool of applicants there are 46 better people than you that won't get in either.
Having elite universities scale up the number of seats available can be done. Grow the pie instead of having the current scarcity mindset. This would actually solve much of the current problems. There is no reason you cannot have the same or better quality of education with more students per university. The only reason this problem exists is that by limiting the number of seats you create artificial scarcity and thus higher value.
Just because it doesn't surprise you doesn't mean it's okay. You have to acknowledge that as an admissions consultant you're part of a small gatekeeping community bubble. Even though I attended one of these schools, I can recognize that universities have been rapidly losing their credibility, and this is only going to accelerate that trend. And by the way, this person is probably more accomplished than I am, even though I am now quite a bit older and my essay was apparently good enough to tick off the checkboxes.
The question you need to be asking is how the university system made an enemy out of someone who is clearly one of the most talented members of his age cohort in the nation. That's a failure no matter how hard you try to explain or justify the status quo. It's time for some real accountability and soul searching from the system, not excuses. Trying to nit pick the essay and pointing out how he should have done X or Y instead is completely missing the point.
Interesting context, thanks for sharing. It sounds like college admissions are broken in the same way SWE interviews are broken.
There was an HN story some years ago about the guy who created homebrew -- a Mac app used by a plurality of Google employees -- being rejected from a job at Google. This seems to follow that pattern: it's not enough that you achieve great things and talk/write about your achievement, you have to stroke the egos of people who could have never accomplished what you did, but still have the power to judge you because the bureaucracy has given them that power.
If the $30M ARR number is true, it's not hard to understand why he wants to talk about it as much as possible. Maybe if you come from family money, you can hear that kind of figure and yawn -- but as someone who came from poverty, I can tell you that this is like if the kid built a rocket out of spare parts in his garage and visited the moon. There's no words for how stunning this is, and everything else in his life must seem trivial by comparison.
I can't understand why the admissions officers would rather read an essay about a kid who volunteered at an animal shelter or something. Anyone can do that.
It has been trendy in Silicon Valley recently to use inappropriate accounting methods to measure ARR.
Joe, a regular guy: Makes $120k at his desk job
Joe, the businessman: Made $20k in 32 days, $228k ARR
Joe, who launched 5 months into development and did 60k in the first 2 weeks: $1.5M ARR
In all three of these examples, Joe's financial outcome is the same. This business does not have any longevity, and all of its revenue is from converting paid advertising of various kinds. It's still impressive, but is most likely a >10x exaggeration on even the lifetime revenue he makes from this. Which is of course circular, because the reason he's doing all this is to make a business out of monetising the audience of people who want to make money.
All of this is clever social climbing, but is clever social climbing the thing that should be rewarded by colleges?
um - I would. Colleges don't want to get panned for hiring a scam artist which is exactly what this is. Unlike VC where that skill is slightly revered.
The app is fake - at best its puffery, and the essay was littered with grammatical errors.
Everything about this kid sends strong signals that one would not want him at their school, workplace, or social environment.
I think the average American today, including the average admissions officer, has a negative view of technology. So, an application that is unequivocally optimistic about technology is unlikely to be well received. I think that that is what happened here. We also have no visibility into letters of recommendation, which are likely a big factor.
This is an incredibly poor take - curious as to how you just completely made up that ridiculous claim? Ironic as well that you think letters of recommendation matter for college admissions when they are perfunctory for probably > 95% of them. Maybe you shouldn't espouse your opinions on this.
Things like this: https://arstechnica.com/tech-policy/2025/04/survey-americans...
I’m also quite sure letters matter for undergraduate admissions. They certainly do at the graduate level.
undergrad and graduate school are completely different...?
His new statement: https://x.com/zach_yadegari/status/1907511557149569190
>The student that runs fake clubs and stacks extracurriculars is admitted over the student that runs a real business.
Yeah. That's how it works. When you do community building and participate in activities in addition to "the grind", people like you more.
This doesn't just apply to academia.
Ahhh this makes sense, another mediocre guy blaming minorities for his own failures
> $30M ARR biz
Unlikely
Probably pointed the Biz AI app at himself to get that estimate.
Clear talent at making bullshit apps that can't possibly work the way he claims maybe
I mean, maybe he deserved to get into more universities, but he did get into solid universities, even if they’re not at the very top. The application pool is very competitive at top universities, and I’m not sure business success should be an automatic in.
What are his talents?
Surely this sort of thing happens all the time? Not to excuse it, but I really don't think any of those rejections was intended to be the personal attack he thinks it is.
clear talent?
I'll bite - I'm an early adopter, and paying user, I paid for the year, but won't renew. For what it's worth, the app UI is dead simple and it makes it easier to track macros. I'll adjust the inputs to what I know I'm eating, and I rarely depend on the "AI camera" I usually just use the UPC barcode scanner. I'm mainly focused on protein intake and making sure I hit those goals. It does a decent job with simple foods, which is healthier for me to eat. I'll break each ingredient down, combine them into meals, then save them. Rinse and repeat for tracking. It's better than a spreadsheet, and I get to see the photos of what I'm eating.
That being said, I'm not going to renew next year. But there is something to this product that is not the "AI" but the simplicity vs. MyFitnessPal which has a ton of features I don't really need.
The critiques are good, but for me, the simplicity of the app is the most attractive part for me.
so why are you not renewing?
Yeah I didn't get either the reason for not renewing
A friend of mine build a similar app last year (https://joineat.app) and it didn't go anywhere (even though it is objectively the nicer app). So there's a lot of luck involved here as well (or maybe he was too early).
For your friends app, I had to go into the app store and then expand the description to view the key features, where it is mentioned that it uses AI similarly as Cal AI. Just based off the initial images of Eat compared to Cal AI, then it's much more clear what Cal AI does compared to yours (besides plastering AI everywhere).
Another thing I noticed is that I saw a random guy on instagram with a rather big following being sponsored by Cal AI. Maybe your friend was unsuccessful in getting his app out there? Although I agree that luck will always play a role, but if the public don't understand what your app immediately does and they believe AI to be pure magic, then sprinkling that everywhere will get something like Cal AI flying.
I still think it is shit from a technical perspective in terms of the validity of amount of calories from a single image and nothing else. But it seems like that's not what people want, inherently because they are lazy. Actually counting calories is much harder long term. If regular people now think that this is magically replacing this process by just snapping a picture of their processed meal, then I can see why it's successful. Although quite depressing...
The worst thing you can do for a bad product is good advertising.
they did distribution well.
I thought about doing this years ago, but without AI, the only way was to have people do the analysis. I thought this was bad karma, as I would end up paying people in Bangladesh to look at the stuff that Americans eat.
A lot of what Americans eat is kinda grim? I couldn't eat the sausage at the hotel breakfast in Little Rock this morning because it tasted like new vinyl smells.
Wrt Bangladesh... I imagine the job might be a little harder during Ramadan.
While technologically cool the app is bullshit. 90% accurate isn't accurate enough for the job and it's effectively making shit up.
Are you eating a 10% calorie deficit or a 10% calorie surplus? Cal AI can't tell you.
Not possible to know accurately enough from a picture. Potentially ever.
My understanding is that even nutrition packaging is often off by up to 30%. Sorry, no source, just what I’ve heard a number of times. If I want to diet I typically build this in and it works well. If they’re actually off by 10% that’s not terrible.
But I tried one of these apps years ago and it went a step further than photos. It used the front facing camera on iPhones to build a 3d model of the food and measure its volume as well. Even that was off by more up to 50% not 10%.
The interesting thing I found, and it’s obvious when you read it but not when you’re trying to diet, is if you don’t layer food on top of itself or other food, you (and a camera based calorie counter) will have a much better understanding of how much you’re eating. Bowls / mounds of food will deceive you.
NIST says "in general NIST’s measurements are accurate to within 2% to 5% for nutrient elements (such as sodium, calcium and potassium), macronutrients (fats, proteins and carbohydrates), amino acids and fatty acids. Its measurements are accurate to within 5% to 10% for water-soluble vitamins (such as vitamin C) and 10% to 15% for fat-soluble vitamins (such as vitamin D)." https://www.nist.gov/how-do-you-measure-it/how-do-you-know-y...
Maybe there's something where they're off by 30%, but how many people even track how much vitamin D they get from food?
There is no way its off that much.
Standard for cutting is about 500 calories deficit, for 1lbs lost a week. Lets say 2500 calories daily standard. That's 20%. If food packaging was off by 30%, food nutrition planning would be worthless, but we know it isn't because we see fairly consistent results from weightlifters (assuming they're actually weighing their food and not eyeballing/using a PoS app like this)
I propose a browser plugin to display calories on all social media food selfie posts.
> The concept is simple: Take a picture of the food you are about to consume, and let the app log calories and macros for you.
> The result is an app that the creators say is 90% accurate, which appears to be good enough for many dieters.
It absolutely cannot be "90% accurate". But I'm sure it seems "90% plausible" to its millions of users.
Incredible that a product like this can exist. Do people just will the fiction into reality?
Incredibly, these are the types of app ideas you'd hear from non-tech "entrepreneurs" in 2012 looking for a co-founder. The problem being, the engineers knew it was impossible. You could fake it I guess by asking Google to search for "similar photos" and getting a plausible calorie count half the time. But the users wouldn't believe it.
We're now at the phase where any impossible idea can be fully marketable by slapping "AI" in the name. ChatGPT feels so magical that we now believe unicorns really do exist.
Truth is so overrated these days.
Exactly! The are so many alternatives, why do we have to place THE truth so highly?
With AI being weaponized by anyone who wants to make a profit, what do you expect?
It doesn’t take AI, just a profit motive. Remember when Russia HACKED THE ELECTION!?!
Even the nutritional labels printed on packaging are only around 90% accurate. It’s all downhill from there.
Just read the Google Play reviews, the app still has a long way to go to be usable.
But it's still a great idea.
Also, they should calculate both the calories and power requirements for each meal analyzed. What I mean is, it should says something like: this burger has 800 kcal and the analysis consumed 1kw of datacenter power. ;)
> But it's still a great idea.
No, it isn't, because it can never work. It is, in general, impossible to determine the calorie content of food by looking at a picture of it.
kw is an instantaneous measurement. Energy usage would be kWh (kilowatt-hours). Considering it would take a tiny fraction of a server’s compute for less than a second this would be very small.
Right, speed vs distance. Still, I'd love to know the numbers.
>But it's still a great idea.
Define "great".
It has $2m revenue, so it's clearly a great idea (at this stage?) financially and 'people love it' (30% retention)
Technically it's a garbage idea, and I'd say they could get class-actioned without good T&Cs. It's literally impossible to determine the sugar and fat content of a meal.
I'd never make it for the latter reason, however you clearly need to believe in the former to make it big haha.
30% retention means that 70% of people who have paid for it didn't consider it valuable enough to pay for.
The $2m figure is unverified but, even if it was, turnover is meaningless without knowing their expenses. If they're burning through £2.1m in LLM compute and marketing then they're losing money.
Plus, the guy seems like a dick so I'm taking his story with an enormous pinch of salt.
"In CS, it can be hard to explain the difference between the easy and the virtually impossible."
It seems we're at a point where this obligatory xkcd [1] is no longer true.
1. https://xkcd.com/1425/
The bird thing was at least _possible_, though, to a reasonable level of accuracy. What they're claiming to do here is completely impossible; there is simply no way of even vaguely accurately determining the calorie content of food based on a picture of the food.
It took a bit more than 5 years and a (single) research team, though.
Anything's possible if you're willing to fake it!
Seems contradictory that there's a market for this since it requires the same individual to simultaneously be concerned about precisely measuring calories yet willing to pay for a method of doing so that's (probably) wildly inaccurate.
The comments from HNers in this case are interesting.
Usually if a teenage hacker builds something, the HNers would respond with enthusiasm, but then, this is a guy who builds *something* and *actually* makes a good business out of it, at the same time maintains his high school life, and all we have is skepticism and discouragement.
It's almost as if people are reading the article and critically evaluating the product.
It is _not_ a good business; the thing does not, and cannot, work.
It's good business, just bad product.
The obvious problem with this is how can it tell how large your meal is or how much butter you put in? I can see it working for fast/junk food, though.
When I learnt machine learning one of the things was continually training the model. Like your spam filter. You show it what is spam and eventually it learns. Is this stuff continually trained on the user's BMI? That's the only way to tell if a diet is working. Or is it just making absolute claims based on universal training data?
Been keeping a food diary for several months now. I did have to spend a bit of time at the beginning working out the calorie content of the food I eat. But after that it's mostly just copy + paste - turned out I was far more of a creature of habit than I thought.
If you want to derive any benefit from doing this you should really be trying to get your numbers correct from the start. I wouldn't leave that to a LLM.
two teenagers and a whole lot of LLMs
This is the guy who's been whining on X about not getting into elite colleges despite his essay being radioactively bad, right?
Yes, same guy. He wrote a list of all his accomplishments, whining about his college rejections. Painfully pretentious individual.
I fed his college essay into ChatGPT and it absolutely roasted him.
Given all the em dashes in his essay, that's probably LLM on LLM violence lol
"Even if there’s a 1% chance I continue my rate of success, wouldn’t they want to take the risk of being able to use my name in the future?"
lol
"60% of the time it works every time!"
Not enough virtue signaled?
https://www.cnn.com/2017/04/05/us/stanford-application-black...
He's given a TEDx talk so I should listen to him, right?
Apparently he ended up going to Yale instead.
That guy walked the talk. It would be virtue signaling if any of us did it, but not him.
He should have just written #BLACKLIVESMATTER 100 times, because that's apparently all it takes to get into Stanford. Honestly though college essays are a bit of a joke, reviewing hundreds of them sounds like torture. The lack of rigor is probably the point though, since it gives the admissions process flexibility to ensure that legacy students get in and they meet their DEI targets.
The Supreme Court said it’s illegal so presumably they’ve knocked that off now.
Hot | Not Hot Dog
(1) That is the paradigm of classification, don't knock it, and
(2) I did some work on a pre-product startup that wanted to build something like this about 10 years ago, when visual recognition was much less developed.
[flagged]
You must be joking.
He's probably AI himself