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

He asked AI to count carbs 27000 times. It couldn't give the same answer twice

diabettech.com

Post reply on HN
Print view View original

81–90 of 329 posts

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#81

Post by falcor84 »

Ekaros wrote: post #36
jaccola wrote: post #6

It’s just an impossible problem. Photons don’t provide sufficient information to determine calories (at least not in any way they could practically be captured). Inside that sandwich could be drenched with olive oil or it could be hollow cheese with lettuce. It’s impossible to tell.

Then it should refuse to answer 100% of time.

I don't think refusal is the right approach. I would much prefer that it respond with something like:

> There is not enough information to make an accurate estimate, but if you'd like, I can take a stab at it. If so, how much effort to put into it?

> Yes, go ahead and spend up to 5mins and $1 to analyze it.

> Done, I've had 100 subagents analyze the image and have arrived at a 95% confidence interval of the portion containing ...

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#82

Post by Aurornis »

This will surprise nobody here, but it’s important to communicate to audiences that are new to LLMs.

This is targeted at people with diabetes because there are AI carb counting apps appearing in app stores

> If you’re using AI carb counting in a diabetes app

These apps are probably not even using the mainstream models used in the study because they would be too expensive for cheap or free apps, and they’re probably forcing structured output to get a response without any of the warnings that an LLM might include if you ask it directly.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#83

Post by nextlevelwizard »

the_duke wrote: post #79
nextlevelwizard wrote: post #55

Earlier quoted context omitted.

As someone who used to do this. OpenAI models refuse to look up calories unless you explicitly tell them to and even then it is a hit and miss even if you tell them exactly what the product is. Easiest way to get good calculation is to just take a photo of the nutrition label or feed that info in by hand. Funny thing is 4o did look up calories but I guess it was too good for this world

I exclusively use thinking mode, which is slower but much more likely to double-check things with web search etc.

Maybe. I stopped using OpenAI a while ago. But taking pictures of the nutrition labels was good enough

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#84

Post by sarusso »

For context: a LOT of people, maybe naively, are now using AI to help them count carbs, and some of these features are already in beta, if not shipping.

That is why I believe this piece from Tim is remarkable: it shows the limitations in a language the diabetes community can understand, and this is why I posted it.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#85

Post by NiloCK »

I think the headline oversells this a little?

The reported variance in Sonnet 4.6's estimates here are actually quite low, and in general terms, not so bad across models. Damn paella.

This does seem like a task well suited to a for-purpose training run against a bunch of labelled data. Is there any reason they wouldn't improve at it?

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#86

Post by renticulous »

2ndorderthought wrote: post #28
jaccola wrote: post #6

It’s just an impossible problem. Photons don’t provide sufficient information to determine calories (at least not in any way they could practically be captured). Inside that sandwich could be drenched with olive oil or it could be hollow cheese with lettuce. It’s impossible to tell.

The average person has no idea this is true. And the average person cannot tell when this is the case. So we have a bunch of people, going their way through school, and then when they get stuck relying on AI. The future is gonna be wild.

Here's technical literacy of population on display. I love these prank examples which show the true education of populace.

https://www.youtube.com/shorts/B7c9qJcRnVk

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#87

Post by furyofantares »

endymion-light wrote: post #43

There's an incredibly serious lack of education with how LLMs & carb-counting works. This entire article would be better suited to astrology.com than hackernews. When I opened it up, I assumed the author would have at least attempted a calculation service, maybe even placed something like the size of the meal into an actual model, using the integration of pre-existing tools that are (slightly more) accurate. Hell - m…

From the text of the article I believe the author is implying there are apps doing exactly this, and so this is why it was studied that way.

Had the author written the article themselves rather than an LLM their motivation probably would have been clearer.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#88

Post by axlee »

"Crema catalana: Three of four models called it “creme brulee” 100% of the time. Only Gemini 3.1 Pro got “crema catalana” — in 3.4% of queries."

----

Wikipedia for Crema catalana:

Crema catalana (Catalan for 'Catalan cream'), or crema cremada ('burnt cream'), is a Catalan dessert consisting of a custard topped with a layer of caramelized sugar.[1] It is "virtually identical"[2] to the French crème brûlée. It is made from milk, egg yolks, and sugar. Crema catalana and crème brûlée are made in the same way.

---

Oh no, my AI can't detect that an obscure clone of a famous dish is indeed the obscure clone, and not the commonly know version.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#89

Post by tsimionescu »

jaccola wrote: post #6

It’s just an impossible problem. Photons don’t provide sufficient information to determine calories (at least not in any way they could practically be captured). Inside that sandwich could be drenched with olive oil or it could be hollow cheese with lettuce. It’s impossible to tell.

This is a bad take. If LLMs are supposed to work as general purpose assistants, as they are being sold as by both the companies making them and by the majority of AI believers, then it is very much a solvable problem. The LLM could give a high level estimate (a sandwich is not going to be 0 Cal, and it's not going to be 5000 Cal, so you can give some kind of range), and then ask for the type of information needed to make a more accurate estimate.

Re: He asked AI to count carbs 27000 times. It couldn't give the same answer twice

#90

Post by emadda »

Related: I created an app to track the molecules in your foods:

https://kg.enzom.dev/

You specify your foods in grams with plaintext (no pictures).

I never liked the "take a picture to measure calories" approach, as you could have 10 table spoons of olive oil which would drastically change the calories but would not show in a picture.

Post reply on HN