164 karma · joined March 9, 2021
If there's something we missed on your food shoot me a DM, I'd love to dig in.
Our app is free to use the most accurate model, ChatGPT is paid for the most accurate model and has usage limits.
Our app plots your data on nice charts and has visuals specific to understanding your data over time visually (e.g. how has my sodium intake been changing day over day or what has my average weekly caloric intake been when deducting active calories from fitness trackers).
Our app integrates with Apple Health and soon will integrate with Android Fit so you can export your data to other apps, share with health professionals, etc.
I've spent the last 10 years of my life researching why this is and how I can help. What I've heard from countless users is that it takes to long to track what they're eating and learn how they can improve.
I've never tried to claim that the selling point of AI is that it's "vastly better", I've just tried to build tools to help people. The voice note feature in our app accompanied by a kitchen scale is the most accurate thing you can do to track nutrition and it actually is much faster than what existed on the market before we launched.
The photo logging feature is more accurate than what most users did before we launched and is by far the fastest way you can track, but yes, it has it's limitations, and unlike our competitors I won't pretend it's perfect. If you're eating out at dinner, and the alternative would be you didn't log the meal, it's a great option.
At the end of the day accuracy actually is not the most important thing if you really care about helping people. Education is what matters. People need to learn which foods and ingredients are the problematic ones and why. Our app accomplishes that better than any solution that existed on the market before we launched.
You especially should not trust an app that does not do any research on the accuracy of it's algorithm or claims to be "consistently accurate" as many of them do currently. The truth is these algorithms have the potential to be accurate when values are averaged out over the long term, but dish to dish they will have occasionally wildly inaccurate results.
Our app has the fruit and veg counters ABOVE the calorie meter on the dashboard. The reason for this is that maximization mindset (e.g. maximizing fruits and veg) is way healthier than a minimization mindset (e.g. minimizing calories or carbs).
We actually even tried to fully remove calories from the app at some point but we had a vast majority of users churn and decided it would be healthier for people who want calorie tracking to stick with our app by having it present, but requiring them to scroll past the features that promote a healthier mindset to get there. Feedback from users has been amazing that they've slowly started focusing more on fruits and veg.
https://openaccess.thecvf.com/content/CVPR2021/papers/Thames...
We've since come up with a much more accurate approach. That said we also try to do some advanced technique to figure out what people were trying to log and not what the amount of food in the photo was. So for example if take a bite out of a bagel, we'll try to say 1 bagel since it's unlikely you wanted to log a bagel less a bite.
We've published in top peer reviewed academic conferences and our algorithm (can't say the same for other apps) IS actually more accurate than people trying to visually estimate portion size, but the truth is both are quite inaccurate.
Most people won't spend the time to track, so photo logging is a faster and easier approximation. If you want more accurate logging you should use the voice logging feature and a kitchen scale (also completely free in our app).
As many mention the goal is to learn, not to tediously track every little thing. Do what's sustainable for you and helps achieve your health and fitness goals.
If people are hitting that goal then they can start moving into more nuanced dietary changes like minimizing adde sugars and sodium, or maximizing nuanced micros and diversity.
We co-authored a paper on this with Google AI and showed it got about 2x the accuracy of a nutritionist because of it.
We can't hit people with the paywall before they've registered because we need to assign the trial to their user record. We've tried adding more language during onboarding but no one reads any of it, they just click through.
You're mistaking challenges in building a global app for malicious intent. I left a job paying a lot more to do this because I wanted to help people.
We'll add something back to the FAQ on this, thank you all for pointing it out.
Our FAQ and pricing pages all list that it is a paid only app. All of our ads explain that it's subscription based. Anyone who asks we're very transparent about it. If there's somewhere else where you think we can list it to make it more clear I'm happy to add it, just not sure where that would be.
You might get a yearly discount offer that is less than $2/month if you get lucky (A/B test split). But that's less than the cost of running the model for people, so hopefully others will consider paying full price.
If anyone wants to check out our app or research its on our site: https://www.snapcalorie.com/
PS: Bitesnap was an awesome app!
Most people don't stay consistent in tracking long enough for any of this to matter, so really it's about what is the most accurate approach to achieve your goal and sustain longer term.
In the study we gave people a variety of dishes to make their estimate on, some they were familiar with, some they were not.
The professionals were nutritionists who had trained in portion size estimation and were shown 2D images on a computer screen.
For what it's worth, we've had a lot of people who have claimed to be very accurate at portion size estimation from a long history of using a kitchen scale. We've paid many of them to do a quiz to see if they're above average accuracy and they have almost always ended up around 40% accuracy or worse.
Count your servings of whole vegetables/fruit. Try to MAXIMIZE these. Yes, maximize in order to lose weight.
It's far easier to track just this small subset of food. If you are maximizing these items, you'll naturally start feeling full and eat less sweets. Try to do this slowly over time, changing your diet dramatically overnight will cause you to hate the process and give up.
Change your diet less than 10% per week, keep eating all of your favorite guilty pleasure foods, just incorporate more healthy foods you enjoy as well, ideally before you eat the less healthy items to give yourself time to start feeling full from them. Slowly find more dishes heavy in vegetables that you like. Try to eat them more often. If you're cooking for yourself or serving yourself, try to increase the ratio of vegetable to other items.
Getting pizza? Maybe do a side salad first or a get a veggie pizza. Don't try to cut the pizza entirely until you're further along in your journey.
Don't stress about it. If you're consistently finding ways to make small changes like this you'll start heading in the right direction over the long haul and your pallet will adapt to enjoy the foods you're not used to slowly.
We published in CVPR (top peer reviewed academic conference for computer vision) and people are on average off by 53% and even trained professionals are still off by 40%. Basically if you want to have a higher level of accuracy you need to use a food scale or something that measure the volume of food, people just can't estimate portion sizes visually.
Oils, cooking fats, hidden ingredients are what people are most concerned about but they actually add far less error to people's tracking than portion. Nutrition5k is the paper we published if you want to check out more details on the breakdown of error most people get when tracking.
People interested in this should also give SnapCalorie a try. Can help with the tracking side of the equation.