LLM generated nutrition for accuracy.
The first item I manually look up is has about double calories listed in the "dataset" versus reality. Honey bunches of oats honey roasted.
Show HN: OpenNutrition – A free, public nutrition database
81–90 of 160 posts
Re: Show HN: OpenNutrition – A free, public nutrition database
#82LLM generated nutrition for accuracy. The first item I manually look up is has about double calories listed in the "dataset" versus reality. Honey bunches of oats honey roasted.
Oof. That makes it completely useless for counting calories. It would be especially bad because the labeling for a lot of ready-made products is available from the manufacturer's website so it should be pretty easy to get it right.
Re: Show HN: OpenNutrition – A free, public nutrition database
#83Earlier quoted context omitted.
[flagged]
It doesn't matter how accurate the models are, it's not a "data set" (in the scientific sense), it's more of a conclusion set. Maybe the conclusions are spot on. Maybe not. I have no idea.
I envisioned many lines of inquiry from HN but the idea that a compressed TSV of nutritional data is not a "dataset" (definition: a collection of related sets of information that is composed of separate elements but can be manipulated as a unit by a computer) was unexpected.
Re: Show HN: OpenNutrition – A free, public nutrition database
#84> Final nutritional data is generated by providing a reasoning model with a large corpus of grounding data. The LLM is tasked with creating complete nutritional values, explicitly explaining the rationale behind each value it generates. Outputs undergo rigorous validation steps, including cross-checking with advanced auditing models such as OpenAI’s o1-pro, which has proven especially proficient at performing high-qu…
Imagine how much more efficient government would be if we just generate all the data with LLMs.
Re: Show HN: OpenNutrition – A free, public nutrition database
#85Earlier quoted context omitted.
Nice! Thanks for responding. >> Outputs undergo rigorous validation steps, including cross-checking with advanced auditing models such as OpenAI’s o1-pro, which has proven especially proficient at performing high-quality random audits. >> there was a lot of manual effort involved in coming to that conclusion with my own effort to review the LLM's reasoning So, the randomly audited entries seemed reasonable to you – n…
> not even the data itself, just the reasoning about the generated data Poor phrasing on my end -- yes, absolutely the end data as well as the reasoning, as the reasoning tends to include the final answer. Maybe I should! Appreciate the feedback.
Thanks again. Mine was an uncharitable interpretation, apologies for that. I appreciate your engagement with critical comments without coming off as defensive or snarky.
This looks like a lot of work and good will were poured into it, and I can see how it can be useful to a fitness focused audience.
You control the messaging on the site and in your apps, and you make it clear that this is not authoritative data. Everything built on top of this needs to have the same messaging, but it has probably been ingested into multiple LLMs already.
I think some sort of licensing requirement that the LLM source of this data be prominently disclosed will not keep this from becoming a source of truth for other datasets, products, and services; but, it is still worth the effort. All you can do is all you can do, right?
Re: Show HN: OpenNutrition – A free, public nutrition database
#86The search is broken on safari, every time it refreshes you lose the focus on the text input, which means you have to click on the search bar after every single character you type. The filters are broken, type "chocolate", chose the M&M's brand, none of the labels return a result despite showing (xxx) > I wanted to investigate the possibility of using LLMs ah, yeah, I guess it makes sense then...
Ah that is an embarrassing bug. Mobile safari does not do that. Thank you for the report, looking to see why that is now. Edit: Should be patched in Desktop Safari now.
It's still erroring in Firefox on macOS and Windows. I see a CORS error on the XHR request
Re: Show HN: OpenNutrition – A free, public nutrition database
#87Earlier quoted context omitted.
It doesn't matter how accurate the models are, it's not a "data set" (in the scientific sense), it's more of a conclusion set. Maybe the conclusions are spot on. Maybe not. I have no idea.
I envisioned many lines of inquiry from HN but the idea that a compressed TSV of nutritional data is not a "dataset" (definition: a collection of related sets of information that is composed of separate elements but can be manipulated as a unit by a computer) was unexpected.
Your response is such a perfect example of why the "data science" movement is a cancer on actual science. So many graduate from programs and boot camps (or just read blog posts) that teach them all the technical mechanics of working with data, but nothing about actual science.
Re: Show HN: OpenNutrition – A free, public nutrition database
#88LLM generated nutrition for accuracy. The first item I manually look up is has about double calories listed in the "dataset" versus reality. Honey bunches of oats honey roasted.
Both products show a 1 cup (41g) and 160 calorie serving size to me?
OpenNutrition: https://www.opennutrition.app/search/honey-bunches-of-oats-h...
Via Manufacturer: https://www.honeybunchesofoats.com/product/honey-bunches-of-...
If you wouldn't mind DM'ing me the barcode you're looking at that would be helpful to understand what the nature of the discrepancy is.
Re: Show HN: OpenNutrition – A free, public nutrition database
#89Earlier quoted context omitted.
It doesn't matter how accurate the models are, it's not a "data set" (in the scientific sense), it's more of a conclusion set. Maybe the conclusions are spot on. Maybe not. I have no idea.
I envisioned many lines of inquiry from HN but the idea that a compressed TSV of nutritional data is not a "dataset" (definition: a collection of related sets of information that is composed of separate elements but can be manipulated as a unit by a computer) was unexpected.
FWIW, I like that you include water content, libraries like google's health connect seem to have completely separate data structures for nutrition and hydration.
Re: Show HN: OpenNutrition – A free, public nutrition database
#90Earlier quoted context omitted.
[flagged]
It doesn't matter how accurate the models are, it's not a "data set" (in the scientific sense), it's more of a conclusion set. Maybe the conclusions are spot on. Maybe not. I have no idea.
Right. At my most generous, this is a dataset about LLM behavior when asked to infer nutritional value. It is in no way a nutrition dataset. It is perhaps useful as half of a benchmark for accuracy, compared to actual ground truth. Unlike a scientist, you're not motivated or resourced enough to create the ground truth dataset. So you took a shortcut and hid it from the landing page.
This workflow, this motivation, this business model, this marketing is an affront to truth itself.