Isn't this just picking up pennies on an active railroad track? You'll win small bets and then get run over once a long tail event completely wipes you out.

I don't think the author is trying to pretend this is some sophisticated strategy you should actually use (note the chudjak in the image on github)

If there's a consistent, sufficiently strong bias towards "yes" and you have enough capital, it doesn't matter as long as you size your bets right and you're able to survive a few train collisions.

If you bet it all on one event yes, otherwise long tail just loses your bet. Downside risk is limited to your bet.