Decoder-only, encoder-only, encoder-decoder: what is each good at, and why does generation use decoder-only?
Three transformer families, one distinction that decides everything: which tokens are allowed to see which. The attention mask is the whole answer, and it explains why GPT generates and BERT does not.
Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.
Three transformer families, one distinction that decides everything: which tokens are allowed to see which. The attention mask is the whole answer, and it explains why GPT generates and BERT does not.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
