Article says that it _can_ be calibrated, it just isn't out of the box. So the title seems contradicted by the body.
> If you want calibrated probabilities you’ll still need to recalibrate Jev’s probabilities on your own data. The good news is that is cheap. A few hundred labeled examples from your actual data can be enough to fit a Platt scaling on top of Jev’s scores.
Yes, good point. I meant that the Jev can't be calibrated for everyone out of the box. I find it important because this is one of their main claims. They literally say
> Outcomes assigned a probability of 0.2 should occur about 20% of the time.
croemer · · focus · HN ↗
> If you want calibrated probabilities you’ll still need to recalibrate Jev’s probabilities on your own data. The good news is that is cheap. A few hundred labeled examples from your actual data can be enough to fit a Platt scaling on top of Jev’s scores.
alexmolas · · focus · HN ↗
> Outcomes assigned a probability of 0.2 should occur about 20% of the time.
and this is not true
croemer · · focus · HN ↗
I understood it as "It is impossible to calibrate Jev".