Why can many AI systems perform sophisticated inference yet still behave as if they continuously forget what they already know?

The question of what knowledge deserves to remain alive is the right framing, because useful memory also needs a deliberate forgetting policy. Persisting and reusing state without provenance, freshness, and invalidation rules turns memory into an amplifier for stale decisions. For agents, I treat write, update, and delete policies as part of the memory architecture, not only the retrieval path.