Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

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


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.


> 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?


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
      }
    }
    ```


[deleted]


Funnily enough, it keeps inventing different excuses to come up with a particular number that is more or less consistent :)

On other tries of the same prompt it happily adds oil, but miscounts other parts


[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.


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.


How does an app know that this piece of chicken cordon bleu is actually filled with more bacon and cheese than chicken?


Try telling a picture of diet coke from regular coke apart.


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.


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.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: