More interesting than arguing a jumble of electrochemical reactions have taste? That may seem more readily familiar but is no less strange if you prod at it. Nonetheless it’s difficult to argue either don’t produce output that has qualities of discernment (ie taste).

The roulette pockets for the model are bigger for some outputs than others. Draw a big enough black box around it and a different one around humans and it's insistinguishable.

Isn't it just arguing that one complex weighted graph was tuned to output tokens that more align with what current day users would define as 'taste'?

I don't think it necessarily says anything about a model itself having 'taste' in some subjective way.

If the fashion changes would the model update with it without retraining? No. So the model doesn't have 'taste' in that sense. It has alignment to current human definitions of taste.

The taste that the complex weighted graph was trained on was better for one than the other I think is the long winded way to say it

It is more capable of writing code I find tasteful and maintainable. It is debatable to what extent it itself has taste. Its outputs just suit my taste more than Codex's do, even though Codex introduces fewer bugs.