Prompt breaks its own pattern

[Gurkenglas]

The strong theoretical reasons for prompts like QA QA QA Q don't hold when the model sees:

user: QA QA QA Q
assistant:

To fix this, try making it see:

user: Q
assistant: A
user: Q
assistant: A
user: Q
assistant: A
user: Q
assistant:

(And I think OpenAI intends the Follow each Q with an A. prefix to be said by system.)