Show HN: I built a Wikipedia based AI deduction game

Posted by brikym 5 days ago

I haven't seen anything like this so I decided to build it in a weekend.

How it works: You see a bunch of things pulled from Wikipedia displayed on cards. You ask yes or no questions to figure out which card is the secret article. The AI model has access to the image and wiki text and it's own knowledge to answer your question.

Happy to have my credits burned for the day but I'll probably have to make this paid at some point so enjoy. I found it's not easy to get cheap+fast+good responses but the tech is getting there. Most of the prompts are running through Groq infra or hitting a cache keyed by a normalization of the prompt.

Comments

Comment by smartypant 5 days ago

but for yes no game you can probably use a cheaper and smaller model and free credits ritght? Anyway, this sounds good geeky.

Comment by brikym 5 days ago

It's all trade-offs between price, speed and accuracy. It's no good using a free model when the latency is 10s+ and the throughput is sub 100token/s and this is often the case on OpenRouter. I have to use a speedy provider like Groq and a small model. Dumber models need a lot more context to correct the inaccuracies. I'm mostly using mid tier models like Gemini 3 flash to generate the boards and then I use the fastest models to answer questions (currently gpt-oss-120b on Groq).

Comment by sagrd 5 days ago

Pretty cool!!

Comment by rockstar2001 5 days ago

this is pretty cool !

Comment by lofaszvanitt 5 days ago

Sluggish as hell. Horrible UX. Overcomplicated.

Comment by jusasiiv 5 days ago

I disagree. UX could be improved but for an alpha version I found out it was easy to use. The main feature "Guess" should be probably more prevalent though. Also for me it did not seem sluggish but that might depend on a lot of factors.

Comment by brikym 4 days ago

Fair. I've made some changes to improve it.

Comment by eddy_cammegh 4 days ago

[dead]