TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Contexto: Find the Secret Word

112 pointsby dgavrilovabout 2 years ago

28 comments

azeembaabout 2 years ago
Seems similar to <a href="https:&#x2F;&#x2F;semantle.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;semantle.com&#x2F;</a> but backed by a different &quot;similarity&quot; calculation.<p>The &quot;bar&quot; visualization is also nicer to track how close&#x2F;far you are.
评论 #35031962 未加载
评论 #35033010 未加载
Zanniabout 2 years ago
Interesting. Took me way too long to realize that &quot;close&quot; is measured semantically, not lexically. A good strategy is to go up and down the ladder of abstraction, e.g. if &quot;car&quot; is close, try &quot;engine&quot; and &quot;vehicle.&quot;
评论 #35031633 未加载
评论 #35031125 未加载
prakhar897about 2 years ago
Few months back, I also tried to create a short puzzle game called Diffudle. The game was basically AI Art + Wordle. You were given an AI generated image and you have to guess the prompt for it.<p>Initially, I got some traction on the site and even some strangers started promoting it.<p>But I soon realized that there is very little marketing spend reward. The customers spend no money and ad revenue per user is abysmal. This means you can&#x27;t use conventional channels and have to rely on people actually finding it fun and recommending it to others.<p>Although it was getting recurring traffic with zero promotion, it still couldn&#x27;t reach a self sustaining level and I had to shut it down.<p>You can see Youtube video of it here: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;uLoMd0TkGKk" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;uLoMd0TkGKk</a><p>The point is: Getting the right puzzle formula is extremely hard and every puzzle will not grow like &quot;Wordle&quot;.
评论 #35035480 未加载
ouidabout 2 years ago
Something is missing, I feel like.<p>The basic idea is sound, but it&#x27;s painful to both start and end a game, and winning isn&#x27;t very satisfying.<p>One of wordle&#x27;s biggest flaws is &quot;the opening&quot;. If you&#x27;re going to have a daily puzzle, it shouldn&#x27;t be exactly the same board to start every day. Games are so fast that this idea doesn&#x27;t totally work there, but I think it would be better if they gave you a starting word every day.<p>The same rule applies here, I think. Your opening move set is basically fixed, and no one is really interested in learning the theory of that. Make the opening less tedious by starting with a couple of random words already played. This has two added benefits. The simplest is that it serves as a tutorial, in all likelihood, if you gave a list of prechosen words and their scores, and a textbox, people would already completely understand the rules of the game without any explanation at all. This is very valuable to a game like this, as it lowers friction.<p>The second benefit is more specific to this game, but it gives players a lot of hypotheses to test new words against from the outset. You want to reward play that deduces the next word not only from similarity to chosen close words, but also dissimilarity from chosen far words. In order to do that though, you have to choose a pretty large disparate set of far words. This hurts your score and is not particularly dependent on the days puzzle (ie you should pick about the same set every time). The game should probably do this for you, at the beginning.<p>Finally, you should reveal how many letters are in the target word. I don&#x27;t want to just probe the model with synonyms. That&#x27;s extremely tedious. give me enough information to make a plausible guess.<p>You could even consider a variant of the game where you&#x27;re only allowed to guess words with the target number of letters, which might actually be mroe fun.
评论 #35036159 未加载
ajjenkinsabout 2 years ago
Got today’s word in 77 guesses. According to the game that’s not a good score, but I was impressed I was able to figure it out at all. Definitely much harder than Wordle.
评论 #35031569 未加载
rubslopesabout 2 years ago
I don&#x27;t think it works very well. Trying not to give too much of a spoiler, today&#x27;s Portuguese word is a noun. When I tried the &quot;verb form&quot; of that noun, I got a score of 207. This led me away from the correct word. I finally got it right in 30 guesses.
评论 #35031840 未加载
Trombone12about 2 years ago
I find redactle and its clones to be better games than the context ones because the similarity measures are inherently without any sense, and so even if you guess the correct word it often feels like pure luck.<p>In redactle winning by pure luck still happens, but at least in hindsight you can tell where you went astray, in contexto the answer often turns out to be &quot;because you aren&#x27;t a high dimensional word embedding trained by Open AI&quot;.
brugidouabout 2 years ago
In french: <a href="https:&#x2F;&#x2F;cemantix.certitudes.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;cemantix.certitudes.org&#x2F;</a>
评论 #35033708 未加载
gauddasaabout 2 years ago
I got red=12, blue=20 and magenta=9283. Also, yellow=33 and orange=93, green=95 and pink=389 if that might help. The word was &quot;flag&quot; but good luck if you are from Nigeria, Pakistan, Brazil, Libya or Mexico.
lucb1eabout 2 years ago
What does the error &quot;this word doesn&#x27;t count&quot; mean? Should the word be countable? Is it known (because &quot;I don&#x27;t know this word&quot; also exists as an error) but not on the top N list?
评论 #35032614 未加载
评论 #35033084 未加载
mmastracabout 2 years ago
I find these to be less-than-ideal puzzles. For example, (no spoilers) today&#x27;s puzzle answer is an abstract concept X, and two very common examples of X score both higher and lower (83 vs 7) than words that are much further away IMO (29).
评论 #35031700 未加载
评论 #35031662 未加载
NathanielBakingabout 2 years ago
I suspect like Wordle, or crosswords for that matter, it will take a certain amount of practice to get the hang of it. But! 43 guesses and I feel good about it.
评论 #35042242 未加载
the_third_waveabout 2 years ago
<i>some word</i> -&gt; a high score<p><i>another word with a meaning close to the previous one</i> -&gt; this word doesn&#x27;t count<p>OK, thanks for making this but I don&#x27;t why I can&#x27;t say <i>the_word_which_shall_not_be_named</i> - it is a perfectly valid word after all even if some feel offended by the mere mentioning of it.
throwaway290about 2 years ago
First couple of words it converted to normalized forms, which I guess was intended to make the game easier? The third word I tried (&quot;restlessnesses&quot;) it just said it doesn&#x27;t know at all.
dfcabout 2 years ago
It&#x27;s weird that Celsius, Kelvin and Fahrenheit were so far apart.
评论 #35031954 未加载
评论 #35033099 未加载
vorpalhexabout 2 years ago
This was fun! I wish it would give me two words as a hint, one in the middle of the stack and one just a bit north of it. Something to get me running.
nbrempelabout 2 years ago
I played contexto.me #168 and got it in 29 guesses and 6 tips.<p>13 8 14
1900-01-01about 2 years ago
When I select give up, I dont see an option to conrifm when it asks me if I really want to.. im using my phone to play.
评论 #35035584 未加载
评论 #35033542 未加载
thdespouabout 2 years ago
The first word I tried was: &quot;fish&quot; it got 44. Nearly getting there...
barking_biscuitabout 2 years ago
Bonus points if you can do some prompt engineering to instruct ChatGPT how to play the game.
_kst_about 2 years ago
I just did a random puzzle, got #12, and got the word in 5 guesses.<p>Pure luck.
jose-clabout 2 years ago
my word was &quot;temperature&quot; and my &quot;voltage&quot; attempt gave a distance of 46, so I was biased and finally gave up. I will try again another day
nfgrepabout 2 years ago
Neat! Must just be compring the distance of embeddings?
ccvannormanabout 2 years ago
I got #2 as Humidity, #22 as Humid, Hint gave me #3 as Celcius, so I guessed Farenheit which was #484. Give up, answer was Temperature. Really? Celcius #3 and Farneheit #484? smh.
评论 #35037167 未加载
sublinearabout 2 years ago
68 guesses, 1 tip. green: 16, yellow: 9, red: 44
zoklet-enjoyerabout 2 years ago
I played contexto.me #168 and got it in 6 guesses.<p>3 1 2
karesztrkabout 2 years ago
My best guess was Water too today. But Temperature as a solution was a way far imo. Can you align the similarity index somehow? Does it evolve? Is it GPT?
评论 #35033346 未加载
spaceman_2020about 2 years ago
It’s a little janky. My word was “temperature”. I got to “water” (no. 29) and then got stuck. Words leading up to it were rain, cloud, storm. Hard to take the leap from there to “temperature”
评论 #35031922 未加载
评论 #35031969 未加载
评论 #35034135 未加载