Live data from Hacker News

Show HN: I've been using AI to analyze every supplement on the market

pillser.com

11–20 of 50 posts

Re: Show HN: I've been using AI to analyze every supplement on the market

#11
found a bug searching for "collagen":

  Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node.
  Something broke. We're working on it, but in the meantime, try reloading the page. If that doesn't work, come back later.

  Error ID: b846e2e2ba3b483ab93f10e72ef76820

  NotFoundError: Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node.
    at ds (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:112074)
    at gs (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:113602)
    at ys (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:113850)
    at gs (https://pillser.com/assets/entry.client-DWgmqxdv.js:1:113728)

Re: Show HN: I've been using AI to analyze every supplement on the market

#12

found a bug searching for "collagen": Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node. Something broke. We're working on it, but in the meantime, try reloading the page. If that doesn't work, come back later. Error ID: b846e2e2ba3b483ab93f10e72ef76820 NotFoundError: Failed to execute 'removeChild' on 'Node': The node to be removed is not a child of this node. at ds (https…

I appreciate you letting me know. I can see it in Sentry as well. It's odd though, it looks like it's coming directly from React. There are no traces in my own codebase. I'll try to isolate it.

Re: Show HN: I've been using AI to analyze every supplement on the market

#13
post #9

I picked Vitamin D as it was an option on the main page. The cheapest offered was $1.1/mg. Costco ( https://www.costco.com/p/-/kirkland-signature-extra-strength... ) sells Vitamin D at less than half that price. On Amazon, the two pack of those is even cheaper. Just an observation.

I think you've mistaken Vitamin D and Vitamin D3 https://pillser.com/search?s=dfbtbc9110&q=%22Vitamin+D3%22 The cheapest price on Pillser for D3 is $0.26/mg

That is odd. When I searched for Vitamin D, it showed me a list (which I could sort by $/mg). That list included Vitamin D, Vitamin D2 and Vitamin D3. I assumed (incorrectly it seems) that this meant that it was doing some sort of prefix match. It seems that the result table highlights the "Ingredient" column, so I assumed (incorrectly) that it was searching that column. However, it doesn't seem to search the "Supplement" column, nor is it doing a prefix match (or substring match) on the Ingredient column. This is just confusing.

https://pillser.com/search?q=%22Vitamin+D%22

Re: Show HN: I've been using AI to analyze every supplement on the market

#14
post #13

Earlier quoted context omitted.

I think you've mistaken Vitamin D and Vitamin D3 https://pillser.com/search?s=dfbtbc9110&q=%22Vitamin+D3%22 The cheapest price on Pillser for D3 is $0.26/mg

That is odd. When I searched for Vitamin D, it showed me a list (which I could sort by $/mg). That list included Vitamin D, Vitamin D2 and Vitamin D3. I assumed (incorrectly it seems) that this meant that it was doing some sort of prefix match. It seems that the result table highlights the "Ingredient" column, so I assumed (incorrectly) that it was searching that column. However, it doesn't seem to search the "Supple…

When you're typing things into search, you're using a freeform search which is going to match the ingredients based on the partial match.

If you want to look for the specific ingredients, you can do so by clicking on the "Ingredients" of the product example: Here are the links for the Vitamin D and D3. https://pillser.com/vitamins/vitamin-d and https://pillser.com/vitamins/vitamin-d3

There is even a Google Sheet that is generated based on the data that we have, although I just noticed that it's not updating properly, so I need to fix that.

Re: Show HN: I've been using AI to analyze every supplement on the market

#16
post #4

This seems more like cataloguing than analyzing I'd love to see a project that actually analyzes every supplement on the market to make sure it actually contains what it claims to, contains it at the listed dosage, and to show anything else found (heavy metals for example). That's not something AI can do for us though since it'd involve physically collecting and testing samples.

Doesn’t that kind of exist already across a couple sites? Thinking consumer labs does this across lots of supplement categories. I have seen a few others too.

Re: Show HN: I've been using AI to analyze every supplement on the market

#17
post #6

Unfortunately, none of these data are usable because (in the US, at least) there is no oversight on labeling accuracy for nutritional supplements. That means I can dump woodchips into capsules and sell them as Multivitamins with 12 vitamins & minerals, and nobody would be the wiser. There is more rigorous testing being done in underground steroid + peptide communities than in legal nutritional supplements. Crazy worl…

Sort've related, but here in Australia pet food manufactures are not required to list the nutritional content of their foods, whereas in the US as I understand it they do.

Re: Show HN: I've been using AI to analyze every supplement on the market

#18
post #6

Unfortunately, none of these data are usable because (in the US, at least) there is no oversight on labeling accuracy for nutritional supplements. That means I can dump woodchips into capsules and sell them as Multivitamins with 12 vitamins & minerals, and nobody would be the wiser. There is more rigorous testing being done in underground steroid + peptide communities than in legal nutritional supplements. Crazy worl…

Supplements should at least be regulated like food. List of ingredients and tests that contains ingredients and doesn't contain anything harmful.

Re: Show HN: I've been using AI to analyze every supplement on the market

#20
> Technical: I started this project when the first LLMs came out. I've built extensive internal evals to understand how LLMs are performing. The hallucinations at the time were simply too frequent to passthrough this data to visitors. However, I recently re-ran my evals with Opus 4.5 and was very impressed. I am running out of scenarios that I can think/find where LLMs are bad at interpreting data.

It's nice to see an AI-centric Show HN product that uses proper evals and cares about data quality.

How did you build your initial data set that you're using for the evals? Bootstrapping a high quality data set is one of the hardest parts of really knowing how an AI product is performing.

Post reply on HN