[viraptor]

> On my own pet eval, writing a fast Fibonacci algorithm in Scheme,

This model was trained on math problems datasets only, it seems. It makes sense that it's not any better at programming.

[pona-a]

The original model, aside from its programming mistakes, also misremembered the doubling formula. I hoped to see that solved, which it was, as well as maybe a more general performance boost from recovering some distillation loss.