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

281–290 of 329 posts

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

#281

Post by tantalor »

harperlee wrote: post #53

There is a lot of hate in the comments but there is some merit to the post existing: 1. Even if the task is unreasonable, it is good to showcase that the LLM will perform poorly - warning not to be used for diabetes. 2. As it is a probabilistic model, the approach was to execute it multiple times and look at the distribution. They also tried to minimize variance: "All at the lowest randomness setting these models off…

> LLM will perform poorly

We've been seeing examples of this constantly since 2022. How many more do we need?

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

#282

Post by inerte »

kalleboo wrote: post #142
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…

> But the author just took pictures of food & expected a realistic response? There are very popular apps on the App Store right now that are going viral among non-techie people that do exactly this, and they have no concept of how AI works. My wife was talking about one and I had to give her a reality check that the AI had no idea what ingredients were used to make the food. And she's a licensed nutritionalist. Studi…

To be fair my expectations is that those apps have done the prompt engineering, and schema, and tools (to query nutrition database), etc... and although they're not 100% consistent, the margin of errors should be narrow to the point that barely matter, and they should do a bit better than a random ChatGPT chat session.

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

#283

Post by tantalor »

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?

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

#284

Post by adrian_b »

johsole wrote: post #255
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…

Thank you for linking the study. Some good news from it. If you weigh the food instead of depending on the package size then the labels become much more accurate!! "Serving size, by weight, exceeded label statements by 1.2% [median] (25th percentile −1.4, 75th percentile 4.3, p=0.10). When differences in serving size were accounted for, metabolizable calories were 6.8 kcal (0.5, 23.5, p=0.0003) or 4.3% (0.2, 13.7, p=…

Moreover, the calorie numbers for raw ingredients are much more accurate than for snack foods, where the amount of each ingredient may vary from nominal, even when the total mass is nominal.

So when you cook yourself and you weigh the ingredients used for cooking, you can know the real calorie content with far more accuracy than when buying ready-to-eat food.

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

#285

Post by cyanydeez »

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…

So, do you think his methodology is closer to a computer scientist, or someone on instagram.

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

#286

Post by wrqvrwvq »

ozbonus wrote: post #98

Before the next galaxy brain shows us all how smart and witty they are by adding the nth sarcastic comment about how obvious this result is, I hope they'll take a moment to consider a few things. Yes, people are using LLMs for this kid of thing. Lots of people. All the time. I've met plenty of them and there loads of apps that offer this kind of "service". The authors are well aware that people are doing this and pro…

Bizarre thread so far. Some threads seem to attract a certain type of boosterism or opinion management. People all rush in to same similar things, without reading the prior comments. Seems designed to wash thoughts into a stream. Maybe coordinated pr or reputation management. It could even be organic but it doesn't seem that way.

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

#287

Post by dredmorbius »

renticulous wrote: post #86
2ndorderthought wrote: post #28

Earlier quoted context omitted.

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

A more robust measurement might be the (former) US Department of Education's "Adult Literacy in the United States" survey, most recently conducted in 2019. The results of this are sobering enough:

https://nces.ed.gov/pubs2019/2019179/index.asp>.

There's a related study of adult technical literacy conducted in 33 OECD nations:

https://www.oecd-ilibrary.org/education/skills-matter_978926...>.

Both show that only a small fraction (5--10%) of adults operate at high levels of literacy (whether of text, numeracy, or technology), and that a large fraction (roughly 50%) operate at a minimal or below-minimal rate.

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

#288

Post by Centigonal »

amazingamazing wrote: post #24

With mass information you could infer much more from pictures. With some sort of standard cube in the picture as well as taking a picture at an angle that emphasizes all three dimensions you could also better estimate the relative volume. It’s tractable I think, but not from a pic alone.

maybe, but not always. I could make two identical-looking sandwiches with very different calorie content by changing the type and quantity of sauce on the inside of the bread. I could give you two "pasta with creamy sauce" dishes that look similar on camera but have different macros by partially swapping Greek yogurt for heavy cream. Dropping a couple tbsp olive oil into my marinara sauce does wonders for flavor but barely affects appearance when plated. Same with lard in my refried beans.

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

#289

Post by nunez »

I don't know why people are using AI to meal track and count calories. MyFitnessPal is dumb easy to use already, and it has, by far, the most robust nutrition facts database out there (they've been in the same for 20 years now; I've been using it since 2008.)

Any nutrition facts these models might use are vectoring either to data from this database or FatSecret. Anything custom, like estimating meals at most restaurants, is going to involve adding and multiplying stuff, and we know how great LLMs are at that.

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

#290

Post by joelthelion »

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…

In my opinion there is also a deficiency of the models who should be able to say "I don't know" when asked for something unreasonable.
Post reply on HN