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

Food and Generative AI

engineering.hellofresh.com

Post reply on HN
Print view View original

91–100 of 100 posts

Re: Food and Generative AI

#91

Post by Xerox9213 »

groggo wrote: post #43
Xerox9213 wrote: post #29

Earlier quoted context omitted.

An aunt signed me up for a few free meals through some promotion. I tried it with an open mind but I found the entire experience infuriating. Most of the meals came with poor quality produce (e.g. tiny unripe avocado — something I never would have grabbed at the grocer) and a silly amount of waste for items I had already. My least favourite part was the recipes. I’m not sure if it was just the small selection of reci…

I agree about the issues - (sometimes) poor quality produce, lots of tiny bits of waste, sometimes template-y feeling meals. Also very expensive, and sometimes not enough food. But overall I really like it. I actually learned a lot about cooking. The meals aren't complicated, and they follow similar patterns, so you start picking up on things. Like seasoning in layers (they tell you to salt & pepper at multiple steps…

I don’t remember the recipe but one of them told me to sauté one thing, and put it in a bowl to cool. Then in another bowl soak something else. Then drain and combine.

Instead I soaked one ingredient, while sautéing the other ingredient. When I drained the first ingredient, I just added the sautéd stuff to that bowl, saving one bowl from washing.

Another thing is the order you cut stuff. If you cut your produce first and then meat you can use the same cutting board. But if you cut meat before veggies (that will stay fresh) then you need a new board, or at least a flip.

Re: Food and Generative AI

#92

Post by ForestCritter »

groggo wrote: post #43
Xerox9213 wrote: post #29

Earlier quoted context omitted.

An aunt signed me up for a few free meals through some promotion. I tried it with an open mind but I found the entire experience infuriating. Most of the meals came with poor quality produce (e.g. tiny unripe avocado — something I never would have grabbed at the grocer) and a silly amount of waste for items I had already. My least favourite part was the recipes. I’m not sure if it was just the small selection of reci…

I agree about the issues - (sometimes) poor quality produce, lots of tiny bits of waste, sometimes template-y feeling meals. Also very expensive, and sometimes not enough food. But overall I really like it. I actually learned a lot about cooking. The meals aren't complicated, and they follow similar patterns, so you start picking up on things. Like seasoning in layers (they tell you to salt & pepper at multiple steps…

A good basic cookbook will teach you alot more, be cheaper and allow you to make your own shopping list and even offer substitution ideas.

Re: Food and Generative AI

#93

Post by ForestCritter »

famouswaffles wrote: post #39
burkaman wrote: post #7

I feel like generating recipe ideas/titles is the easy part, and advanced AI techniques are not necessary. Even the article notes that there is not really any difference between 1 round of training and 40 rounds of training with their model. Actually generating a recipe is obviously much harder, and should be effectively impossible unless you include a humanoid robot that can cook and taste. I think the best you coul…

>Actually generating a recipe is obviously much harder, and should be effectively impossible unless you include a humanoid robot that can cook and taste. It's not because this necessary information is already implicit in the sum of all the data it is trained on.

There are alot of bad recipes floating around out there. Recipe books are often geared to teaching you how to cook not just what to cook. There's techniques to cooking that affect how recipes come out. A good recipe book will teach you how to treat ingredients, how they interact with each other and then give you ideas on how to put them together.

Re: Food and Generative AI

#94

Post by ForestCritter »

famouswaffles wrote: post #71
uoaei wrote: post #68

Earlier quoted context omitted.

I don't think the commenter's understanding of LLMs is relevant here. It's what the authors of TFA think LLMs are for and, arguably more importantly, what kinds of problems (nails) they think about when presented with the idea of applying LLMs (hammer). It's a bit ridiculous that this is the best they can come up with, and I don't really think the idea is worth defending, especially by telling other people that they…

His/Her primary assertion is that it is impossible for a LLM to generate novel recipes without physically tasting it first. His/her assertion is wrong and one easily corrected by understanding a LLM is and does. It's not a perfect predictor so it's not impeccable for all conceivable situations but GPT-4 can already generate novel recipes that taste nice. This is not some far flung science fiction ability.

Salt to taste, cook until brown, kneed until the dough is no longer sticky, everything about cooking is tasting and feeling. Moreover everybody has differences in their tastes and consistency preferences. Good recipe books teach you how to use ingredients and apply that knowledge to recipes and how to modify those recipes to your personal preferences. Sure an LLM can generate novel recipes but without the premise of taste, texture and food pairing tuned in to personal preference, the novel recipe is a crap shoot in the dark. The reality is, the more you learn to cook, the less you need recipes and a good cookbokk will teach you alot more than a pile of recipes.

Re: Food and Generative AI

#95

Post by ForestCritter »

guhidalg wrote: post #17
burkaman wrote: post #7

I feel like generating recipe ideas/titles is the easy part, and advanced AI techniques are not necessary. Even the article notes that there is not really any difference between 1 round of training and 40 rounds of training with their model. Actually generating a recipe is obviously much harder, and should be effectively impossible unless you include a humanoid robot that can cook and taste. I think the best you coul…

One problem I have is recipe clustering by ingredients. I want to minimize the different ingredients I need to buy so I can get some economies of scale while shopping. I don't know of any service that does this, I have been thinking about building it for my website but I haven't figure out what is a good UI for it.

better homes and garden cookbook with the red and white checkered cover. The basics are all there and the ingredient lookup is in the index. Say I lookup potato, all the potato recipes are in the index. It also offers substitutions. I have an older version and a newer version.

Re: Food and Generative AI

#96

Post by ForestCritter »

reidjs wrote: post #73

Unrelated to the article, but I have had great success using LLMs to generate recipe. Here's how it goes: "I have a ton of onions, what can I make" (LLM provides like 4 options) "Ok, give me a recipe for French Onion Soup" (LLM provides recipe) "I don't want to use my oven for the bread, can I use my air fryer?" (LLM provides an alternative approach using the air fryer instead) Thanks LLM! That was way better than so…

my cookbook on my counter has an index of onion recipes...

Re: Food and Generative AI

#97

Post by ForestCritter »

codekansas wrote: post #28

XKCD for this https://xkcd.com/720/ Less tritely - I do find it fascinating how problems that would've been independent research endeavors can now be subsumed by large language models. Rather than building a big dataset of protein, calories, etc., just ask ChatGPT

or get a cookbook...

Re: Food and Generative AI

#98

Post by ForestCritter »

justus_fc wrote: post #5
breakingciphers wrote: post #2

Curious to hear people's thoughts on AI applications in the food space.

Im the founder of foodforecast and we help the food industry (ie bakeries, gastronomy, supermarkets) with demand predictions, so they only need to produce what they will sell. Our AI uses historical sales data, weather and holiday data, resulting in a much better prediction quality (>95% accuracy) than simple statistical approaches. This way we can reduce food waste by 30% on average.

and there goes the death of new flavors...

Re: Food and Generative AI

#99

Post by NeoTar »

chefandy wrote: post #86
NeoTar wrote: post #74

Earlier quoted context omitted.

> and use volumetric measurements instead of weights Sorry to pick up on one sentence of an interesting long comment, but this is a pet peeve on mine when having to rely on American recipes. There seems to be an obsession on using volumetric measurements for things which really should be done in mass units - flour, sugar, sometimes even ingrediants like grated cheese. European recipes in my experience tend to use mos…

Yeah it's definitely a big thing with recipes designed for American home cooks. Just like using SAE measurements, it's a chicken and egg thing. Maybe one in ten US home kitchens has a food scale because our recipes don't generally use weight measurements, and recipes don't generally use weight measurements because one in ten US home kitchens has a food scale. If you're making an investment in publishing a cookbook, i…

Thanks for the reply !

With respect ingredients such as onions, I am concerned that what I think of as a medium onion, may not be a medium onion in other countries/cultures. Like, I generally will consider an onion of about 5cm (2 inches) as medium-sized, but if I am off by 1cm from the author's perceptions that's 50% less, or 70% more!

If a recipe could say '125g chopped onion (1 medium onion)' that would be so useful - catering to the geeks like me and normal home cooks!

Re: Food and Generative AI

#100

Post by chefandy »

NeoTar wrote: post #99
chefandy wrote: post #86

Earlier quoted context omitted.

Yeah it's definitely a big thing with recipes designed for American home cooks. Just like using SAE measurements, it's a chicken and egg thing. Maybe one in ten US home kitchens has a food scale because our recipes don't generally use weight measurements, and recipes don't generally use weight measurements because one in ten US home kitchens has a food scale. If you're making an investment in publishing a cookbook, i…

Thanks for the reply ! With respect ingredients such as onions, I am concerned that what I think of as a medium onion, may not be a medium onion in other countries/cultures. Like, I generally will consider an onion of about 5cm (2 inches) as medium-sized, but if I am off by 1cm from the author's perceptions that's 50% less, or 70% more! If a recipe could say '125g chopped onion (1 medium onion)' that would be so usef…

I get it... you're anxious that it's going to be the wrong amount so you want a very specific number... but that specificity doesn't yield commensurate accuracy. Even if everyone put in exactly 125g of plain yellow onion, the variance in age, when it was harvested, soil conditions, etc. would yield more variation than changing the weight... it just usually doesn't matter that much with onions. This is most apparent with strong ingredients like garlic and herbs: one strong small clove of garlic will easily overpower 2 larger mellower cloves of garlic if used raw, but will often have less comparative influence if cooked... not too many people outside of the restaurant world would even know how to judge whether a small piece of raw garlic was stronger or mellower than average. If you're using a flour with a standardized grind and protein level, using weight for a loaf really matters.

The most common manifestation of this disconnect is in cooking times. Unless you've got completely standardized ingredients, preparations, storage temperatures, etc. which is very difficult outside of large food service organizations, (and why so many restaurants are willing to pay so much to huge restaurant suppliers like Sysco for mediocre food... it will always cook the same way,) cooking times will almost always be the wrong answer. People always ask questions like "how long do I cook a thick ribeye steak?" and I always say "until its done." There's a general perception that very accurate cooking times will yield very accurate results, but that's so not true. What's the size and shape of the steak? What's the water content of the steak? Has that changed since you pre-salted it too far in advance? Refrigerator temps vary tremendously: what's yours at, how long has the steak been out.

People like cooking times and precise measurements for imprecise ingredients because it gives them a sense of control, but it's a false sense of control. when the only way to get that sense of control is learning how to tell when the food is done by yourself.

Post reply on HN