An AI Memory Should Come with an Expiry Date
Persistent AI memory saves repetition but can preserve stale assumptions. Build a Memory Boundary Card to govern purpose, source, correction and expiry.
Human-centred technology—from everyday life to deep engineering.
Persistent AI memory saves repetition but can preserve stale assumptions. Build a Memory Boundary Card to govern purpose, source, correction and expiry.
Support demand is not merely overhead. Repeated calls, abandoned forms and unnecessary visits can reveal defects that transaction dashboards never see.
Human–AI agreement can hide anchoring or stubbornness. A better workflow preserves both provisional views, examines divergence and records why judgement changed.
A backup can preserve every byte and still fail the person who needs it. A small recovery rehearsal reveals missing permissions, unreadable formats and knowledge trapped in one person's head.
A documented in-car comparison shows why a well-designed physical control can preserve tactile skill, reduce visual demand and keep human attention on the road.
A device can remain physically sound yet become useless when its app, API or cloud service changes. Follow the dependency stack—and learn what predicts a longer life.
A smart device should preserve essential local control when its app, account, internet connection or vendor disappears. Manual mode is infrastructure for agency and resilience.
How large language models can create adaptive physics courses, generate responsive exercises, and organize a personal scientific knowledge database—without replacing verification, mathematical discipline, or human judgment.
A practical architecture for using LLMs to create tailored physics courses, manage a personal knowledge base, retrieve scientific concepts, and safely control the underlying database.
This week’s note is exceptionally long, but for a critical reason: The GenAI Divide is not just an interesting trend; it is the absolute core of our present work and…