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

Show HN: OpenNutrition – A free, public nutrition database

opennutrition.app

Post reply on HN
Print view View original

41–50 of 160 posts

Re: Show HN: OpenNutrition – A free, public nutrition database

#41

Post by adamas »

joshdickson wrote: post #34
Xiol32 wrote: post #27

Earlier quoted context omitted.

You need to add a disclaimer for this data. People could rely on them being accurate, and you simply can't prove they are.

There is a large disclaimer that states, among other things, "We strive to ensure accuracy and quality using authoritative sources and AI-based validation; however, we make no guarantees regarding completeness, accuracy, or timeliness. Always confirm nutritional data independently when accuracy is critical." on every page on the website where that kind of in-depth data is available.

At that point, if you are not sure a data point is accurate, should you really display it ? You have no proof appart from "The LLM said it was ok" which is kind of poor.

Re: Show HN: OpenNutrition – A free, public nutrition database

#43

Post by volkk »

hombre_fatal wrote: post #28
volkk wrote: post #24

Super cool. Would you consider an API?

Why would you want an API if they give you the data? https://www.opennutrition.app/download

yeah that's awesome, but I think staleness could be a concern? i'm sure there will be updates to nutritional values, additions of new foods, etc. API gives me the latest without having to redownload/rehydrate every time. plus its a way for OP to monetize further for all of the apps that utilize nutritional data.

Re: Show HN: OpenNutrition – A free, public nutrition database

#44

Post by rob »

yamihere wrote: post #36

>> User-generated databases can be unreliable >> Foods discovered via these searches are fed back into the database, Aren’t LLMs also unreliable? How do you ensure the new content is from an authoritative, accurate source? How do you ensure the numbers that make it into the database are actually what the source provided? According to the Methodology/About page >> The LLM is tasked with creating complete nutritional v…

Not really sure how the author thinks anybody who tracks their calories/macros seriously is going to trust a website that literally just makes up values for the vitamins, minerals, etc:

> TL;DR: They are estimates from giving an LLM (generally o3 mini high due to cost, some o1 preview) a large corpus of grounding data to reason over and asking it to use its general world knowledge to return estimates it was confident in, which, when escalating to better LLMs like o1-pro and manual verification, proved to be good enough that I thought they warranted release.

Re: Show HN: OpenNutrition – A free, public nutrition database

#46

Post by hombre_fatal »

criddell wrote: post #40
hombre_fatal wrote: post #38

Earlier quoted context omitted.

Because you want to be able to log the calories/nutrients of the food you're eating before it's cooked into a dish. You don't want to have to cook your bacon and then measure its mass before you know how many calories it has when you can just log the raw form before you cook it.

You don't want to do that, but unless you are consuming all the rendered fat that's what you do to get an accurate value.

Sure you do. And if you don't consume all of the grease, then you have some overestimation error in your tracking which is evened out by (but usually dominated by) all of your underestimation errors, like every time you forget to log the squirts of oil in the pan or that handful of mixed nuts or every time you eat out.

Having to cook your food first, take it out, measure it, and put it back in the dish you're making before you can estimate content doesn't seem like a recipe (pun) for habit forming here. Nor is it viable for anything but the most basic dishes like individually pan frying large ingredients.

Re: Show HN: OpenNutrition – A free, public nutrition database

#47

Post by johnisgood »

Just at a quick glance...

How can a large egg (50 g) contain 147 g choline?

https://www.opennutrition.app/search/eggs-eeG7JQCQipwf

Additionally, on https://www.opennutrition.app/search/brown-lentils-VwKWF7CQq... it says:

> Unlike larger legumes, they require no pre-soaking and cook in 20-30 minutes, making them ideal for soups, stews, and salads

That is not necessarily true. Based on my experience, it does require pre-soaking, otherwise you will have to cook it for a long time, as opposed to red lentils (which is done under 15 minutes, no pre-soaking needed), although red lentils taste more like yellow peas.

In any case, I think this could be really useful, once accurate enough. One could even implement other features on top, such as a calorie tracker and so forth, but that is a huge project on its own.

I wish you luck!

Re: Show HN: OpenNutrition – A free, public nutrition database

#48

Post by Rooster61 »

Does this have an API? Reason I ask, I would kill to have a dynamic recipe scanner that could plug into recipe databases (namely ones that can accurately scrape recipes from the web) and instantly give you a nutritional rundown of the ingredients, as well as any changes to the nutrition that could occur due to the cooking process. It would make tracking what I eat a breeze, and really give solid insight into the macros and micros I'm consuming.

Also, why the app focus? Having the main functionality exist in the Apple/Android store space rather than as a SaaS option seems like an interesting choice.

Re: Show HN: OpenNutrition – A free, public nutrition database

#49

Post by joshdickson »

yamihere wrote: post #36

>> User-generated databases can be unreliable >> Foods discovered via these searches are fed back into the database, Aren’t LLMs also unreliable? How do you ensure the new content is from an authoritative, accurate source? How do you ensure the numbers that make it into the database are actually what the source provided? According to the Methodology/About page >> The LLM is tasked with creating complete nutritional v…

> Those rigorous validation steps were also created with LLMs, correct?

Not really. I do explain in the methodology post how good o1-pro is at the task, but there was a lot of manual effort involved in coming to that conclusion with my own effort to review the LLM's reasoning, and even still, o1-pro is not perfect.

Re: Show HN: OpenNutrition – A free, public nutrition database

#50

Post by ramon156 »

johnisgood wrote: post #47

Just at a quick glance... How can a large egg (50 g) contain 147 g choline? https://www.opennutrition.app/search/eggs-eeG7JQCQipwf Additionally, on https://www.opennutrition.app/search/brown-lentils-VwKWF7CQq... it says: > Unlike larger legumes, they require no pre-soaking and cook in 20-30 minutes, making them ideal for soups, stews, and salads That is not necessarily true. Based on my experience, it does require pr…

I think they meant mg. Eggs are 293/100gr
Post reply on HN