Semantic Calculator
AI
word embeddings
SHOW HN2025
176points
172comments
#386of 3,837 in 2025
Top 11%of 2025 by points
How HN took it
CuriousMostly questions and neutral comments
16 positive, 69 neutral or asking, 4 mixed, 28 critical, out of 117 comments about the project. Thread score -0.09.
Execution: 6 for, 16 againstIdea: 7 for, 9 againstPerformance: 0 for, 2 againstDesign: 1 for, 0 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Fun and engaging ranked results
From 3 comments
This is super fun. Offering the ranked matches makes it significantly more engaging than just showing the final result.
skeptrune on HNnoodle+tomato=pasta this is pretty fun
adzm on HNA few favorites: wine - beer = grape juice beer - wine = bowling astrology - astronomy + mathematics = arithmancy
clbrmbr on HN
Nice interface
From 1 comment
First off, this interface is very nice and a pleasure to use, congrats! Are you using word2vec for these, or embeddings from another model? I also wanted to add some flavor since…
spindump8930 on HN
Objections
Many results are nonsensical or biased
From 4 comments
man - intelligence = woman (36%) woman + intelligence = man (77%) Oof.
e____g on HNdoctor - man + woman = medical practitioner Good to understand this bias before blindly applying these models (Yes- doctor is gender neutral - even women can be doctors!!)
doubtfuluser on HNshows how bad embeddings are in a practical way
yigitkonur35 on HNHuh, that's strange, I wanted to check whether your embeddings have biases, but I cannot use "white" word at all. So I cannot get answer to "man - white + black = ?". But if I…
ignat_244639 on HN
Only nouns work; plurals and non-nouns fail
From 1 comment
Yes, word in red = word not found mostly the case when you try plurals or non-nouns (for now)
nxa on HN
Requests
Show word definitions in the UI
From 1 comment
This might be helpful: I haven't implemented it in the UI, but from the API response you can see what the word definitions are, both for the input and the output. If the output…
nxa on HN
Questions
Why do some inputs return red circles or no answer
From 2 comments
What does it mean when it surrounds a word in red? Is this signalling an error?
cabalamat on HNI'm getting Navralitova instead of queen. And can't get other words to work, I get red circles or no answer at all.
TZubiri on HN
Alternatives named
ChatGPT or LLMs
From 2 comments
For fun, I pasted these into ChatGPT o4-mini-high and asked it for an opinion: ``` data + plural = datasets data - plural = datum king - crown = ruler king - princess = man king…
n2d4 on HNJust use a LLM api to generate results, it will be far better and more accurate than a weird home cooked algorithm
maxcomperatore on HN
Infinite Craft
From 2 comments
Neat! Reminds me of infinite craft https://neal.fun/infinite-craft/
antidnan on HNThis is super neat. I built a game[0] along similar lines, inspired by infinite craft[1]. The idea is that you combine (or subtract) “elements” until you find the goal element.…
jumploops on HN
Contexto
From 1 comment
Reminds me of the very annoying word game https://contexto.me/en/
anonu on HN