It's more than context-rot.

If you ask a vague ignorant question, you get back authoritative summaries. If you make specific request, each statement is taken literally. The quality of the answer depends on the quality of the question.

And I'm not using "quality" to mean good/bad. I mean literally qualitative, not quantifiable. Tone. Affect. Personality. Whatever you call it. Your input tokens shape the pattern of the output tokens. It's a model of human language, is that really so surprising?