All of human cooking compressed into 2 megabytes
josefchen
399 points
159 comments
May 27, 2026
Related Discussions
Found 5 related stories in 96.8ms across 8,637 title embeddings via pgvector HNSW
- KV Cache Compression 900000x Beyond TurboQuant and Per-Vector Shannon Limit EGreg · 44 pts · April 21, 2026 · 48% similar
- Cook: A simple CLI for orchestrating Claude Code staticvar · 107 pts · March 19, 2026 · 46% similar
- TurboQuant: Redefining AI efficiency with extreme compression ray__ · 509 pts · March 25, 2026 · 45% similar
- Show HN: Broccoli, one shot coding agent on the cloud yzhong94 · 56 pts · April 22, 2026 · 44% similar
- Transformers Are Inherently Succinct (2025) bearseascape · 45 pts · May 04, 2026 · 42% similar
Discussion Highlights (20 comments)
leontrolski
Neat. I'm trying to compress recipes into little schematics https://leontrolski.github.io/recipes.html
haaz
Published by Kaikaku, a London based startup doing automated restaurants and cooking
suddenlybananas
I don't see why the title needs to be quite so grandiose.
epsteingpt
The work is very interesting. The title is misleading. A better title would be: "all of human ingredients compressed into 1,800 primitives" There is little to substantively nothing about the actual cooking: preparation methods, proportions, etc. But the idea that tomato goes well with beef the whole world over is very interesting and useful for creating flavors that will go together, perhaps surprisingly. It will be a nice resource in the future.
Retr0id
> [Claude] performed all ingredient classification under deterministic decoding (temperature 0–0.1) Not that it matters much in this context, but low-temperature is not the same thing as deterministic.
pfdietz
Cooking condensed beyond the point of usefulness. It's another book for Zach Weinersmith.
antirez
Odd not including French and Italian recipes.
jweisbin
"human cooking"? ewww
1970-01-01
11 sources is not "all of" anything. You have a sample. The title is horrible. Fix the title please.
skinfaxi
Cooking/recipes seems like it would be an excellent application for a specialized model.
vitto_gioda
Why haven’t you analyzed Italian recipes in Italian?
nyokki
As someone learning to cook from recipes in multiple languages, this is really cool. Curious how it handles the same ingredient called by different names (e.g., "scallion" vs "green onion" vs "long onion").
baalimago
Great, so now chefs are being replaced too..!
throwme_123
I would not trust a model/corpus about food that includes English and German, but excludes Italian and French
coldtea
>from 11 sources spanning seven languages, English, Chinese, Russian, Vietnamese, Spanish, Turkish, Indonesian, German, and Indian-English So hardly "all of human cooking"...
vrganj
You can use it to browse flavor combinations here, seems quite neat! https://epicure.kaikaku.ai/ That being said, I'm not excited about the idea of this being used to automate cooking somehow. Food, to me, is part of what makes us human, where we express our soul for lack of a better word. The idea of taking that away feels like robbing us of our humanity.
cuechan
I don't really understand, what the Graphs on page 9 and 13 represent, but they look somewhat like a world map with the continents. I wouldn't be surprised if there's actually a geographic connection. A lot of ingrediants are probably more prevalent in certain world regions.
bhouston
I saw this on X/Twitter. I do not believe that human cooking, and all of its techniques and ingredients and the various ways that things can be prepared in different cultural contexts can be compressed in to 2 megabytes. It is sort of like saying here is a 1GB model that can do tool calling and coding and then you try it out and it barely functions. Yes, it technically is a 1GB coding model, but it isn't a good one.
jonstewart
Jacques Pepin's knuckles don't compress.
moffers
At uncook we’re in the middle of glamming up our ingredient normalization pipeline, so this is VERY welcome right now