[HN Gopher] A solver for Semantle
___________________________________________________________________
A solver for Semantle
Author : evakhoury
Score : 46 points
Date : 2026-02-18 19:25 UTC (3 days ago)
(HTM) web link (victoriaritvo.com)
(TXT) w3m dump (victoriaritvo.com)
| a_shovel wrote:
| I was hoping this would have some application for human solving.
| I gave up on Semantle because I couldn't figure out any sort of
| strategy.
| pokpokpok wrote:
| it was mentioned above, but give it another chance using the
| pimantle UI that provides a 2d map, much more enjoyable:
| https://semantle.pimanrul.es/
| jml7c5 wrote:
| Regarding Semantle, I found that Pimantle
| (https://semantle.pimanrul.es/) is a much more satisfying
| implementation to actually play. It provides a 2D visualization
| of guesses, which lets you see the clusters and lines of
| similarity more clearly.
| AgentCIPHR wrote:
| Oooh I love this, thanks for sharing.
| tptacek wrote:
| This has Peter Norvig sudoku energy, in that it describes a game
| that is tricky enough for humans to solve that it's become a
| whole pastime, but is a trivial solver away from reliably
| defeating, and with a tiny amount of code. Once you see what
| they're doing with this, you're like, oh of course. Very cool.
| OisinMoran wrote:
| This is super interesting, thanks for sharing! I did a similar
| thing a few years ago which I'd been meaning to properly finish
| and share, and your post was the inspiration needed to make mine
| public (albeit still in a state much too messy for my liking,
| hopefully having it public will force me to improve it).
|
| We took fairly different approaches, but I really enjoy the
| visual explanation element of yours! Well done.
|
| My investigation stemmed from wondering if the seemingly useless
| 1st, 10th, and 1000th nearest word similarity scores were enough
| to uniquely ID the word. Turns out--yes, pretty much! It's
| effectively just a kind of reverse engineering, similar to how
| you also made your own version of the game. Can definitely
| improve on a lot.
|
| Tried today's puzzle and got it in two (first was 999/1000).
|
| Here's my code & write up: https://github.com/OisinMoran/Solving-
| Semantle/blob/main/Sol...
| tantalor wrote:
| Semantle is weird. Words you would expect to be close are not.
| For example: castle is far from moat and stone. Why?
| OisinMoran wrote:
| I think the way the similarity is done is based on word co-
| occurrence and the dataset used is news articles. So you can
| imagine that not a lot of news articles mention castle in that
| context.
| tantalor wrote:
| I guess I get really frustrated when the rules say you are
| scored on "how close you are to the secret word, based on
| your word's meaning" with very little explanation what that
| means.
|
| Then you have cases that drive me crazy, like the guess
| "food" is very far from the secret word "cupcake", and "toy"
| is actually very close to "cupcake". What?
|
| Like, come on. This is not playable or fun.
|
| For reference, these are the words close to "cupcake",
|
| https://proximity.clevergoat.com/nearest/Y3VwY2FrZQ%3D%3D
| keetal wrote:
| For french speakers who want to play a similar game, there is
| Cemantix (https://cemantix.certitudes.org/), also based on
| Google's word2vec.
| omoikane wrote:
| There was a solver years ago that used a similar technique, where
| you get similarity scores from three fixed words ("giant enemy
| crab") and it finds the target word instantly:
|
| https://github.com/manimino/semantle-crab
|
| The solver website seems down, but the archived version still
| works:
|
| https://web.archive.org/web/20220421184123/https://crab.mani...
| bscphil wrote:
| I like this article a lot, but if I can put forward one mild
| criticism, it seems to depend entirely on having _exactly_ the
| same measure of semantic distance for word pairs as the original
| generator. In that case, as the post shows, you only need several
| guesses to eliminate all possibilities other than the correct
| one, just like you only need a few GPS satellite locks to pin
| down your location.
|
| It would be interesting to see a solver that works more like a
| human player, where it requires the "warmer" "colder" information
| from different guesses to hone in, rather than being able to
| simply look up which words have the _exact_ semantic distance (+
| /- some fudge factor) from the guess.
| pvillano wrote:
| Great visualizations
___________________________________________________________________
(page generated 2026-02-21 23:01 UTC)