[troupo]

> But the mystery is really why, in setups like these, Claude is much more likely to say "An" than "A" in the first place.

Because in the training set you're likely to see "an astronomer" than a different combination of words.

It's enough to run this on any other language text to see how these models often fail for any language more complex than English

[shawabawa3]

You can disprove this oversimplification with a prompt like

"The word for Baker is now "Unchryt"

What do you call someone that bakes?

> An Unchryt"

The words "An Unchryt" has clearly never come up in any training set relating to baking

[miraculixx]

Attention is all you need.

[troupo]

The truth is somewhere in the middle :)