Fun. Scored 35/36.

Have you considered an endless mode where you keep playing until you make a mistake?

Density, conductivity, x-ray. Density alone won't rule out bars that are spiked with tungsten.

The parabola of a telescope mirror generally deviates from a sphere by tens of micrometers at best. Figuring happens after grinding and after polishing. Slumping is neat, but I've heard from the grognards that they can shatter if the temperature changes too quickly.

Were you thresholding the naïve Bayes score or doing soft distillation?

> They are so many orders of magnitude too slow for so many uses

On hardware with AES primitives this is simply false. Yes, embedded cases are different. There's some neat work on probabilistic computing that uses a xorshift RNG in hardware. These are specialized use cases that probably aren't your use case. Use the right tool for the job and try to be less condescending.