This was so fun! What a delight, thank you.
After the first round I wanted to keep playing, so habitually I just tapped whichever button that most closely resembled ‘play again’, and it took me a couple questions to understand that it was a different mode. Maybe putting “type the OLDEST answer”, or “the deepest cut” above the prompt box would help.
Also the model’s feedback was surprisingly astute! I expected “incorrect”, but got “Help was a top-selling Beatles album, but it sold under 20 million copies.” Love learning during games.
I was playing the "Future" section and put "Milliway's" from The Hitchhiker's Guide series when it asked for a fictional restaurant; it only gave me 10 points and said it was from 70s. Milliways is very explicitly positioned in time at the end of the universe, so I should've been awarded maximum points there :)
Hi thanks for the feedback! In Past and Future, what counts is when the thing first came out, not when the story takes place, so Milliways counts as 1978 (the radio series). I agree it's not obvious with sci-fi though o I think I'll add a mention somewhere
This would be fun to play in groups, comparing answers after each round, but I think the strict timer would make that impossible. Maybe add a different mode?
Also I love the through yet swift feedback on incorrect answers. Did you leverage decision models for that?
Plenty of good answers were rejected, especially where typos were concerned. On the coffee shop question, CK's coffee shop wasn't found and Waffle House was rejected, but Paul's was a top answer? Paul's also serves breakfast food. Seems arbitrary. Memphis Colosseum was rejected probably because the proper spelling is Coliseum. But how could it not find it from "Memphis Colosseum"? It's easily found (and the spelling corrected) in Google Search.
Hey, thanks a lot for the feedback! Most answers are first checked against a fixed list, to avoid making too many LLM calls. Unfortunately, for latency and playability reasons, we can't do much deeper online searches: every call would cost a lot and take too long. So about 1 to 1.5% of answers end up judged a bit unfairly, but we're actively working on improving the model.
Thanks again for your feedback!
That makes sense to me; people commonly buy tickets for local events while on vacation. Perhaps it should detect and warn about that kind of ambiguity, though.
Thanks a lot for the feedback chrome tells the page exactly where the keyboard is and firefox doesn't... and in that case my layout keeps the question above the visible area. I'll try to fix it
Thank again!
The judging for the "newest" seems a bit odd - for viral toy I answered 'Labubu' which the AI dates to 2015, which might be when they were first introduced to the market, but not when they had their viral hype.
For newest palace I answered Berliner Stadtschloss which was opened in 2020, but the AI dates it back to 1443
Both dates are actually "right" from the game's point of view: Labubu was created in 2015 (the viral hype came way later), and construction of the Berliner Stadtschloss started in 1443, the 2020 opening is the reconstruction.
In Past and Future, what counts is when the thing first came out/was created, and the dates come from the Wikipedia API. I agree it's not obvious when the question says "viral" or "newest" though, so I'll make those questions more precise. Thanks again for playing! :)
Similarly it asked for Formula 1 World Champion, in the "most recent" game, so I put in Lando Norris, who won last year, but the answer is Max Verstapen because he was born in 1999 and Lando was 1997, it took me a few minutes to even figure out what the leaderboard was saying..
1824th of 1824. Dead last with a score of 60 that your game handed me on a misspelling. I typed Windy's and it changed it to Wendy's and awarded a correct answer.
I’m from a non-English-speaking country, but I understood how to play right away. I did struggle a bit with questions about things like British TV series, though. The game has a wonderful atmosphere, and I really enjoyed playing it!
Lots of fun, but one really annoying bug that makes it hard to play: anytime I have an answer that isn’t accepted, and then go to type in a new answer, the keyboard completely covers the text box which makes it impossible to delete or edit the previous answer! Safari on IOS 26.6.2
I love that I could justify my answer to it - spoiler below
I chose CompuServe for oldest file sharing service, and it told me that it was an online service not a cloud file hosting service. I then answered "CompuServe had file sharing" and I received 100pts
I'm really glad you liked it! That's one of the big advantages of using LLMs instead of relying on a fixed list of answers. Thanks so much for playing! :)
The agent is too helpful, I got away with stuff like "The one with the southmost shinkansen" for rarest Japanese city, which it substituted for the answer to that (which I didn't know)
Thanks you for the feedback, the concept doesn't come from Krillion or from me, there was already a game called Pointless on TV way before that, and Sky is straight up Family Feud, Past and Future are our own concepts
And the graphics, even if the code and the implementation were obviously written with AI like 100% of people coding a big project today, they're human made
But the Abyss mode looks almost identical to krillion - from the very concept of trying to guess rare answers, to the nautical diving theme, down to the almost-pixel-art style..?
It's incredible to suggest that this wasn't based on either Krillion, or that both games were based on something else.
(To be clear, I'm not accusing you of explicitly lifting the concept - but that's the problem with using AI to generate too much, it'll obviously re-use what it's seen before.)
edit: actually, you say "A large part of the code was written with AI tools, but the artistic direction the concept and every choice design are human-made" - it's just wildly improbable for the two to look and feel so similar.
Great work. I’m bored of Krillion because the AI judge sucks and the animations are WAAAAYYYYY too long. This feels like an upgrade in every way. Will add to my daily rotation of snacks, thank you :)
Rarest is terrible. I absolutely know that baked ube is a street food, and way less likely to be guessed than Udon, and yet I'm penalized for nobody else guessing it yet?
I didn't even play latest and oldest, because that's just a guessing game.
Beijing being 3rd less popular answer for "Asian capital city" is pretty bizarre.
Also the model’s feedback was surprisingly astute! I expected “incorrect”, but got “Help was a top-selling Beatles album, but it sold under 20 million copies.” Love learning during games.
Great work, the lot of you!
Good point about the mode switch. My girlfriend actually warned me about it, and I told her it wouldn't be a problem but she was right haha.
We'll take your advice and give it a clearer name.
And I'm really glad you liked the feedback. Thanks again for playing! :)
This would be fun to play in groups, comparing answers after each round, but I think the strict timer would make that impossible. Maybe add a different mode?
Also I love the through yet swift feedback on incorrect answers. Did you leverage decision models for that?
'HashiCorp is not named after a person; the name comes from "hash" (computing) and "corp"'
Nah it's named after the founder Mitchell Hashimoto.
Per the wikipedia summary https://en.wikipedia.org/wiki/HashiCorp
> The company name HashiCorp is a portmanteau of co-founder last name Hashimoto and Corporation.
The aesthetics are nice, but I think the idea of the game itself is seriously flawed.
The question was "Name something that's expensive when travelling" in the most common answer category.
I wrote "tickets", meaning plane tickets, and it categorized my answer as "Entrance fees (you)" instead of the top answer of "Plane ticket".
Both dates are actually "right" from the game's point of view: Labubu was created in 2015 (the viral hype came way later), and construction of the Berliner Stadtschloss started in 1443, the 2020 opening is the reconstruction. In Past and Future, what counts is when the thing first came out/was created, and the dates come from the Wikipedia API. I agree it's not obvious when the question says "viral" or "newest" though, so I'll make those questions more precise. Thanks again for playing! :)
Some clarity there would be much better
On my iphone17e, some answers don't scroll so I can't click to continue to the next question.
1824th of 1824. Dead last with a score of 60 that your game handed me on a misspelling. I typed Windy's and it changed it to Wendy's and awarded a correct answer.
I'm not sure how to feel about that.
I chose CompuServe for oldest file sharing service, and it told me that it was an online service not a cloud file hosting service. I then answered "CompuServe had file sharing" and I received 100pts
I like the fact no account is required.
Die Hard (you) 26.7%
I recall playing an identical game a few months ago, also on the HN front page.
https://www.krillion.org/
It's incredible to suggest that this wasn't based on either Krillion, or that both games were based on something else.
(To be clear, I'm not accusing you of explicitly lifting the concept - but that's the problem with using AI to generate too much, it'll obviously re-use what it's seen before.)
edit: actually, you say "A large part of the code was written with AI tools, but the artistic direction the concept and every choice design are human-made" - it's just wildly improbable for the two to look and feel so similar.
I didn't even play latest and oldest, because that's just a guessing game.
I agree that the rarest wasn't nearly as entertaining or fun. Perhaps that one needs a list to pick from.