01 The Problem of Memory in AI Making an AI remember looks like a storage problem. I learned, by getting it wrong, that it is three problems — and none of them is solved with more bytes. Memory in personal agents 8 min 02 Why Remembering Everything Is Bad Saving everything looks like prudence. But there is a kind of bug that never shows up in any log: the system does exactly what it was told and the results get worse. Too much memory is that bug. Memory in personal agents 9 min 03 The Difference Between Conversation, Memory and Knowledge For months, my system had two opposite defects I treated as one: it forgot too much and it remembered wrong. The fix was not code — it was realizing I was operating three layers with a single knob. Memory in personal agents 9 min 04 Memory as a Database Problem The question that broke Atlas's first memory was simple: why did I decide this? The system had the answer stored — and could not answer me. This essay is about what was missing. Memory in personal agents 10 min 05 Memory as a Ledger I destroyed a decision without ever pressing delete. Editable memory collapses three different truths into one mutable sentence — and a personal ledger is what pulls them back apart. Memory in personal agents 11 min 06 Provenance: Every Memory Needs a Source A memory can be correct and still not deserve trust. Without a traceable origin, it cannot be revised, challenged or used by agents with responsibility. Memory in personal agents 8 min 07 Governed forgetting Forgetting is not a memory failure. It's policy: the system decides what stops influencing the present, records the decision, and can reverse it. Without that, the ledger becomes an uncurated archive. Memory in personal agents 9 min 08 Compaction as memory design The ledger never erases, so it only grows. Compaction is the mechanism that keeps the weight of the past from freezing the present — rebuilding active state without losing the chain of provenance. Memory in personal agents 6 min

Search

Searches both languages