Welcome to your interview.
The question is on your right: Explain Attention in Transformers. Take a moment with it first.
Talk your thinking through with me if you like - when you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes). Discussion and graded submissions share your five interviewer interactions, so spend them well.
You are discussing transformer basics in the context of building LLM-powered features. A teammate asks why transformers can relate one token to another even when they are far apart in the sequence.
How do attention mechanisms work in transformer architectures?