I love to see these cases of dim insert random industry executives thinking they have to somewhat integrate LLMs in their marketing or they would be left behind.
It's not a sound use case. LLMs have no concept of taste or conception of cooking. Just because they can string the words together into something that looks like recipe, doesn't mean it's actually something more useful than a randomly generated output.
I mean, I have used chatgpt to generate recipes and I can tell you it’s surprisingly effective.
It’s particularly good for a grocery-list kind of problem: “I have X and Y in my kitchen, what could I make?”
Ingredient ratios and cooking times/heats usually need tweaking, but the broad strokes are often quite good.
Definitely a strong use case there, although I don’t know how you would refine to actually good recipes. Probably need a human in the loop testing and tweaking, or at least gut-checking.
It works as long as the user understand what it’s doing and to discard the advise when it goes awry. If you don’t then you might end up with absurd or dangerous results. The average user is not a HN-level genius.
It could very easily tell you to incorrectly cook chicken for example and get salmonella
If you're willing to drink bleach because the internet told you to, then you had very serious problems before LLMs and you'll still have serious problems if we ban LLMs. The internet is full of incredibly harmful health and dietary advice that is 100% human-generated.
Developers have a duty to users, but that duty is not Hippocratic; we have no obligation to only release products that are absolutely safe under all circumstances. My nailgun will fire a 4" nail through my skull without hesitation, but I'm not outraged by that fact. I don't demand a nailgun with a complex skull-detection system, or a moratorium on all nailgun development until we're confident that a nailgun will never drive a nail through something that it shouldn't. The manufacturer warns me "this is a nailgun, it'll put a nail through damned near anything including flesh and bone, so don't be a dummy" and society recognises my right to take that risk.
I'm completely fine with an LLM recipe generator that, if asked, will create a recipe for a bleach and rat poison cocktail. It'd be nice if the model was a bit more refined, but I'm fine with an unrefined model so long as it gives a suitably prominent disclosure to the effect of "this is a large language model, it isn't human and has no common sense, so apply your own common sense to any output it gives".
This is really the crux of the GenAI hype cycle for me. Other than code auto-completes, and cool one-off uses ("Generate me a picture of a clown on Mars!"), I'm yet to see much of a use-case.
At my work, we're trying to use GenAI to make a chatbot for internal info sharing/onboarding/etc. I am constantly asking myself how this will ever be better than a well-written company wiki/employee handbook with a search function.
No but I often ask Bard for advice. E.g. "can you think of any Indian recipes with courgette and peas" gives some good suggestions of what to do with left over food, that would be hard to do with a cookbook.
No it’s not.
Tell me any other technology as imperfect and prone to unpredictable failure as LLMs that executives in all walks of industry would want to implement so badly in production in one way or another.
I think there’s a lot of chatGPT collective stupor at play, and a serious lack of second level thinking when it comes to estimating possible brand damage.
Or you could query a database to get faster, cheaper, more accurate results. Recipes already have ingredients separate from instructions, this is a solved problem. I’m certain I’ve bumped into websites which do exactly that. Using an LLM for outputting recipes from a list of ingredients is as necessary as using a blockchain.
