One of the things you might like to steal for future iterations of this is its testing process. To demonstrate that you know the rule, before you’re given the green light to move on, it quizzes you on a large set of examples and you have to be able to categorize them all correctly.

I feel like this game has the opposite problem of 2-4-6. In 2-4-6, it’s very easy to come up with a hypothesis that appear to work with every set of test cases you come up with, and thus become overconfident in your hypothesis.

In your game, I had trouble coming up with any hypothesis that would fit the test cases.

Another fun programming exercise is to do the other direction: have the user come up with a rule, and make the program come up with examples to try to test its hypotheses. (You want the program to generate examples that falsify half the remaining probability-mass.)

Usability feedback: please make the Enter key also submit, not just clicking the Test button!

Here’s something we can run in our url bars to get this now

```

javascript:document.getElementById(“theInput”).addEventListener(‘change’, ()=> test())

```

Relatedly there’s a nice little singleplayer zendolike for android here https://play.google.com/store/apps/details?id=org.gromozeka1980.caterpillar_logic&hl=en

I’d recommend it

One of the things you might like to steal for future iterations of this is its testing process. To demonstrate that you know the rule, before you’re given the green light to move on, it quizzes you on a large set of examples and you have to be able to categorize them all correctly.

I feel like this game has the opposite problem of 2-4-6. In 2-4-6, it’s very easy to come up with a hypothesis that appear to work with every set of test cases you come up with, and thus become overconfident in your hypothesis.

In your game, I had trouble coming up with any hypothesis that would fit the test cases.

Another fun programming exercise is to do the other direction: have the user come up with a rule, and make the program come up with examples to try to test its hypotheses. (You want the program to generate examples that falsify half the remaining probability-mass.)