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

301–310 of 329 posts

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

#301

Post by azakai »

jihadjihad wrote: post #297
pkaye wrote: post #258

Earlier quoted context omitted.

There is a parameter in LLMs called temperature that controls creativity/randomness. If you set it to 0 it makes the model deterministic. I think some LLMs expose this as a tunable parameter.

> If you set it to 0 it makes the model deterministic. No, it doesn't. It can help make the model more deterministic, but it does not guarantee it.

The hardware can also add nondeterminism. GPUs reorder operations, leading to different results.

Vendors might also be running A/B testing or who knows what, even when you ask for a temperature of 0.

But, if you run a fixed model with temperature 0 on your local CPU, it will be deterministic (unless there are bugs).

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

#302

Post by CGMthrowaway »

andrewvc wrote: post #189
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…

One of the biggest gaps is that people don't understand that food labels are allowed by the FDA to be off by up to 20% in terms of the number of actual calories! In the real world you need to calibrate your behavior with the results. Are you gaining weight? You'll need to eat less if you want to lose any. You can do all the math with nutrition labels and macros you want but that's all theoretical. See this study belo…

The errors either cancel out (if error in both directions) or they work in one direction ("bad" foods like junk systematically underestimate calories, "good" foods like protein powder systematically overestimate calories).

Either way, if you count calories and compare to your weight gain/loss over a few weeks and adjust your calorie target as warranted, assuming the types of food you are eating do not change drastically (e.g. you calibrated on regular diet and now have started an elimination diet), the error bars can be basically ignored.

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

#303

Post by notahacker »

endymion-light wrote: post #248
swiftcoder wrote: post #198

Earlier quoted context omitted.

The app the study is based on is open-source, so you yourself can verify that it does indeed just call a frontier model with the same prompts used in the study

That's not really the same thing as what I'm saying - which is to investigate the applications specifically advertising AI calorie counting capabilities

They investigated an open source application specifically advertising carb counting capabilities, replicated its prompts and API calls in a way optimised to collect data from 26000 queries (which is a lot to do using a GUI!). They also note other people have already done [necessarily] smaller scale studies of the commercial AI carb counting apps and been similarly unimpressed by the responses.

This is all in the first few paragraphs of a preprint paper describing the research in considerably more detail which is linked at the bottom of TFA

Meta: enjoying nearly half this HN thread being arguments that surely people care about what's in their food don't ask ChatGPT for comment instead of looking it up properly, and most of the rest of it being people who apparently care what's in a research paper asking HN for comment instead of looking it up :)

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

#304

Post by nclin_ »

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…

He was directly addressing apps that claim to do so, and proving that they can't, with laypeople who might have diabetes as the target audience.

It's more a data-driven pub test, I think it explains itself well.

The question is - are those apps actually so simplistic? Or is this a strawman.

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

#305

Post by andrewvc »

CGMthrowaway wrote: post #302
andrewvc wrote: post #189

Earlier quoted context omitted.

One of the biggest gaps is that people don't understand that food labels are allowed by the FDA to be off by up to 20% in terms of the number of actual calories! In the real world you need to calibrate your behavior with the results. Are you gaining weight? You'll need to eat less if you want to lose any. You can do all the math with nutrition labels and macros you want but that's all theoretical. See this study belo…

The errors either cancel out (if error in both directions) or they work in one direction ("bad" foods like junk systematically underestimate calories, "good" foods like protein powder systematically overestimate calories). Either way, if you count calories and compare to your weight gain/loss over a few weeks and adjust your calorie target as warranted , assuming the types of food you are eating do not change drastic…

Exactly! My point was that despite the precision of calories we should really think of them as ballpark estimates .

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

#306

Post by lukeschlather »

tsimionescu wrote: post #261
lukeschlather wrote: post #251

Earlier quoted context omitted.

The thing is it doesn't really prove LLMs can't do this, it proves no existing frontier LLMs can do this. The part where they talk about sampling multiple runs is interesting - it suggests to me that in the next few years as the reasoning process is improved the models may be able to do that autonomously. My mind really is going to using a dedicated object detection models fine-tuned with nutrition information, but I…

Per some people, LLMs of the future can do literally anything that's possible to do. They could create quantum computers powered by fusion power. That has nothing to do with the question being asked, can you rely on an LLM today to help you track carbs as a diabetic? This is very explicitly what the article is all about. Potential future LLMs are entirely irrelevant.

This isn't something so fanciful as fusion power, this is reasonably something that might be within the capabilities of object detection transformers. Whether a different prompt/finetuning with a good dataset could make this work is very relevant here.

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

#307

Post by Aurornis »

tantalor wrote: post #283
Aurornis wrote: post #82

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 f…

Who in Al Gore's Internet is new to LLM in 2026?

Most of the world.

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

#308

Post by comes »

gus_massa wrote: post #212

Let's start with the wrong title: > I Asked AI to Count My Carbs 27,000 Times. It Couldn’t Give Me the Same Answer Twice. If you look at the image https://www.diabettech.com/i-asked-ai-to-count-my-carbs-2700... it clearly shows some repeated values. I guess AI like multiples of 5 or 10 or something. It would be nice to look at the raw tables. > A cheese sandwich on a plate. Here’s one that should be easy. Two slices…

The difference between them is that crème brûlée is made heavy cream instead of milk and it tastes better. But my Catalan friends would kill me for this blasphemy… so you didn’t hear that from me.

They are both covered by burned sugar and therefore indistinguishable(!) visually.

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

#309

Post by endymion-light »

tsimionescu wrote: post #268
endymion-light wrote: post #141

Earlier quoted context omitted.

I don't believe the authors of this study are stupid. If there are apps targeting people with diabetes that claims to count your carbs with AI, why haven't those been analysed? That would be a far more effective claim. I based the study off of the clickbait article that they wrote about the study - i'll read through the study to see whether they analyse that, but it would be far more effective to see if the 'carb-cou…

The linked "click bait" article explains this very clearly as well. It clearly explains the methodology: they took the prompt sent to an LLM by a popular open source carb counting iOS app and sent it, together with five different pictures of food that a typical person might take, to all of the frontier models, and checked the responses. They also explain the purpose: to check the possible accuracy of this approach ta…

I didn't take anything as an attack on LLMs. I took it as a severe misunderstanding of how technology works. I specifically outline that I would like to see the margin of error even when integrating actual apps that claim to achieve results, rather than using tools that don't.

None of my claim perceives anything as an attack on LLMs, which shows a mischaracterisation on your part of my entire point.

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

#310

Post by endymion-light »

muwtyhg wrote: post #273
endymion-light wrote: post #210

Earlier quoted context omitted.

i mean it's more like "AI can solve this one problem, but it needs X, Y, Z, because it's not a omnipotent god entity" "I tried it without any of those things and it didn't work - this is worthless tech!" I don't know if more accurate calorie counting using AI exists - but it's like being upset that the screwdriver isn't gluing wood. AI is far more than frontier LLMs.

In this case, what is the 'X, Y, Z' that the apps are providing that the model is not?

Theoretically:

- A queryable large vector database containing calorie counts for specific meals.

- A vision model specifically trained on food images with labelled data containing approximate calorie counts.

- OCR model allowing reading of barcodes + calorie information.

A model trained to ask for additional context & information (e.g for pasta - please provide a photo of the original sauce tin/ect), (please approximate the weight of X meat)

I don't know how accurate integrating all of those aspects would be - and you could argue the end user would probably be incredibly annoyed and it wouldn't be a good app - but I'd argue you'd at least need that if you're developing an app for diabetes management.

Post reply on HN